# Video Action Recognition on UCF101

Source: [Video Action Recognition on UCF101](<https://www.sota2.com/research/sota/video-action-recognition-on-ucf101>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-28T07:25:44.300Z

Evaluation of video action recognition performance on the UCF101 dataset, reporting Top-1 Accuracy.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Video Action Recognition |
| Dataset (including any stated split) | UCF101 |
| Metric | Top-1 Acc |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 165 of 165 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Top-1 Acc](<https://www.sota2.com/research/sota/video-action-recognition-on-ucf101.md?metric=Top-1%20Acc>): Higher is better; unit: PERCENT.

- [R@1](<https://www.sota2.com/research/sota/video-action-recognition-on-ucf101.md?metric=R%401>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc | Result date | Report paper |
| --- | --- | --- | --- |
| VideoMAE V2 | 99.6 | Not recorded | 68fa7b991e209131cea89646 |
| MoTIF-ST | 98.4 | Not recorded | 68fa7b991e209131cea89646 |
| MoTIF | 98 | Not recorded | 68fa7b991e209131cea89646 |
| Global CBM | 97.5 | Not recorded | 68fa7b991e209131cea89646 |
| MoTIF | 97 | Not recorded | 68fa7b991e209131cea89646 |
| Ours ViT-L | 96.9 | Not recorded | 68fa6ee71e209131cea42c8a |
| Ours ViT-L | 96.6 | Not recorded | 68fa6ee71e209131cea42c8a |
| Ours ViT-L | 96.4 | Not recorded | 68fa6ee71e209131cea42c8a |
| SMILE | 96.4 | Not recorded | 68fa77b21e209131cea74d3d |
| NoFrame | 96.4 | Not recorded | 68fa7b991e209131cea89646 |
| UMT | 96 | Not recorded | 68fa77b21e209131cea74d3d |
| TSM | 95.9 | Not recorded | 68fa7b991e209131cea89646 |
| ViCLIP | 95.2 | Not recorded | 68fa77b21e209131cea74d3d |
| MoTIF | 94.8 | Not recorded | 68fa7b991e209131cea89646 |
| ViFi-CLIP | 94.6 | Not recorded | 68fa77b21e209131cea74d3d |
| ILA | 94.2 | Not recorded | 68fa77b21e209131cea74d3d |
| AIM | 94 | Not recorded | 68fa77b21e209131cea74d3d |
| ELo | 93.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| HR2G-shot | 93.7 | Not recorded | 68fa7a8c1e209131cea83d8c |
| CLIP | 93.6 | Not recorded | 68fa77b21e209131cea74d3d |
| OmniVL | 93.2 | Not recorded | 68fa6dbd1e209131cea3bbb4 |
| ViFi-CLIP | 92.7 | Not recorded | 68fa6ee81e209131cea42cef |
| GDT | 92.5 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| GDT | 92.5 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| MVP-shot | 92.2 | Not recorded | 68fa7a8c1e209131cea83d8c |
| CVRL | 92.1 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| X-CLIP | 92 | Not recorded | 68fa77b21e209131cea74d3d |
| ActionCLIP | 91.4 | Not recorded | 68fa6ee81e209131cea42cef |
| XCLIP | 91.4 | Not recorded | 68fa6ee81e209131cea42cef |
| MIL-NCE | 91.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| MIL-NCE | 91.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CLIP-FSAR | 91.3 | Not recorded | 68fa7a8c1e209131cea83d8c |
| CoCLR † | 90.6 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CoCLR † | 90.6 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CLIP image-FT | 90.5 | Not recorded | 68fa6ee81e209131cea42cef |
| ViCC-R+F | 90.5 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-R+F | 90.5 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViFi-CLIP | 90 | Not recorded | 68fa6ee81e209131cea42cef |
| A5 | 89.9 | Not recorded | 68fa6ee81e209131cea42cef |
| FiT | 89.6 | Not recorded | 68fa6dbd1e209131cea3bbb4 |
| MotionFit | 88.9 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-R+F | 88.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-R+F | 88.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CLIP text-FT | 88.1 | Not recorded | 68fa6ee81e209131cea42cef |
| UMT | 88 | Not recorded | 68fa77b21e209131cea74d3d |
| SeLaVi | 87.7 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| SeLaVi | 87.7 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CoCLR † | 87.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CoCLR † | 87.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| Pace Pred | 87.1 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| Pace Pred | 87.1 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| XDC | 86.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| XDC | 86.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCLIP | 86.7 | Not recorded | 68fa77b21e209131cea74d3d |
| CLIP text-FT | 85.8 | Not recorded | 68fa6ee81e209131cea42cef |
| A5 | 85.7 | Not recorded | 68fa6ee81e209131cea42cef |
| ViCC-R+F | 85.7 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| MCN | 85.4 | Not recorded | 68fa6a991e209131cea2938c |
| CLIP image-FT | 85.3 | Not recorded | 68fa6ee81e209131cea42cef |
| ViFi-CLIP | 85.1 | Not recorded | 68fa6ee81e209131cea42cef |
| MCN | 84.8 | Not recorded | 68fa6a991e209131cea2938c |
| MemDPC | 84.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-RGB | 84.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-RGB | 84.3 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| X-Florence | 84 | Not recorded | 68fa6ee71e209131cea42c8a |
| SMILE | 83.8 | Not recorded | 68fa77b21e209131cea74d3d |
| XCLIP | 83.7 | Not recorded | 68fa6ee81e209131cea42cef |
| iCaRL (IM) | 83.53 | Not recorded | 692e732fd6b0dd33429328b7 |
| TimeSformer | 82.9 | Not recorded | 68fa6dbd1e209131cea3bbb4 |
| CLIP text-FT | 82.8 | Not recorded | 68fa6ee81e209131cea42cef |
| ViCC-RGB | 82.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| ViCC-RGB | 82.8 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| MIL-NCE | 82.7 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| MIL-NCE | 82.7 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| RTT | 81.6 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| RTT | 81.6 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CoCLR | 81.4 | Not recorded | 68fa6a991e209131cea2938c |
| CoCLR | 81.4 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| CoCLR | 81.4 | Not recorded | 68fa6b0d1e209131cea2bbe2 |
| SpeedNet | 81.1 | Not recorded | 68fa6b0d1e209131cea2bbe2 |

### VideoMAE V2

Top-1 Acc: 99.6. Result ID: 6a042eec47f34ce924e9e319.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f171e209131cea43db1.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### MoTIF-ST

Top-1 Acc: 98.4. Result ID: 6a042eec47f34ce924e9e316.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

Recorded evaluation configuration: {"Backbone":"PE-G/14"}. This record does not assert independent reproduction.

### MoTIF

Top-1 Acc: 98. Result ID: 6a042eec47f34ce924e9e315.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

Recorded evaluation configuration: {"Backbone":"PE-G/14"}. This record does not assert independent reproduction.

### Global CBM

Top-1 Acc: 97.5. Result ID: 6a042eec47f34ce924e9e312.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68f91e209131cea1f6a0.md>)

Recorded evaluation configuration: {"Backbone":"PE-G/14","Evaluation Protocol":"Supervised"}. This record does not assert independent reproduction.

### MoTIF

Top-1 Acc: 97. Result ID: 6a042eec47f34ce924e9e314.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

Recorded evaluation configuration: {"Backbone":"PE-L/14"}. This record does not assert independent reproduction.

### Ours ViT-L

Top-1 Acc: 96.9. Result ID: 699082bd3a6c3148490116a4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Implementation](<https://github.com/whwu95/Text4Vis>)

Recorded evaluation configuration: {"shot":"All"}. This record does not assert independent reproduction.

### Ours ViT-L

Top-1 Acc: 96.6. Result ID: 699082bd3a6c3148490116a3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Implementation](<https://github.com/whwu95/Text4Vis>)

Recorded evaluation configuration: {"shot":"2"}. This record does not assert independent reproduction.

### Ours ViT-L

Top-1 Acc: 96.4. Result ID: 699082bd3a6c3148490116a2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Implementation](<https://github.com/whwu95/Text4Vis>)

Recorded evaluation configuration: {"shot":"1"}. This record does not assert independent reproduction.

### SMILE

Top-1 Acc: 96.4. Result ID: 69955f273badfaffe6513eab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Implementation](<https://github.com/fmthoker/SMILE>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"K400 \[35\]"}. This record does not assert independent reproduction.

### NoFrame

Top-1 Acc: 96.4. Result ID: 6a042eec47f34ce924e9e318.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69a11e209131cea23371.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### UMT

Top-1 Acc: 96. Result ID: 69955f273badfaffe6513ea9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5652b.md>)

[Implementation](<https://github.com/OpenGVLab/unmasked_teacher>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"K700 \[8\]"}. This record does not assert independent reproduction.

### TSM

Top-1 Acc: 95.9. Result ID: 6a042eec47f34ce924e9e317.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66381e209131cea0ee93.md>)

[Implementation](<https://github.com/mit-han-lab/temporal-shift-module>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ViCLIP

Top-1 Acc: 95.2. Result ID: 69955f273badfaffe6513ea7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cd9.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"Intervid-10M \[84\]"}. This record does not assert independent reproduction.

### MoTIF

Top-1 Acc: 94.8. Result ID: 6a042eec47f34ce924e9e313.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7b991e209131cea89646.md>)

Recorded evaluation configuration: {"Backbone":"ViT-L/14"}. This record does not assert independent reproduction.

### ViFi-CLIP

Top-1 Acc: 94.6. Result ID: 69955f273badfaffe6513ea4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Implementation](<https://github.com/muzairkhattak/ViFi-CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"None"}. This record does not assert independent reproduction.

### ILA

Top-1 Acc: 94.2. Result ID: 69955f273badfaffe6513ea6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa705a1e209131cea4a883.md>)

[Implementation](<https://github.com/Francis-Rings/ILA>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"None"}. This record does not assert independent reproduction.

### AIM

Top-1 Acc: 94. Result ID: 69955f273badfaffe6513ea5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e801e209131cea405f5.md>)

[Implementation](<https://adapt-image-models.github.io/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"None"}. This record does not assert independent reproduction.

### ELo

Top-1 Acc: 93.8. Result ID: 69a1402d35dfcabb00e5c7b8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67211e209131cea147fc.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"S3D","Param":"8.8M","Res":"224","Frames":"32","Modality":"V+T"}. This record does not assert independent reproduction.

### HR2G-shot

Top-1 Acc: 93.7. Result ID: 6a17ede4fbc373592c11479a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d8c.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-based CLIP","Few-shot Setting":"5-way 1-shot"}. This record does not assert independent reproduction.

### CLIP

Top-1 Acc: 93.6. Result ID: 69955f273badfaffe6513ea1.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"None"}. This record does not assert independent reproduction.

### OmniVL

Top-1 Acc: 93.2. Result ID: 69a149c335dfcabb00e6077b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbd1e209131cea3bbb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6dbd1e209131cea3bbb4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"linear probing"}. This record does not assert independent reproduction.

### ViFi-CLIP

Top-1 Acc: 92.7. Result ID: 699084843a6c314849011f5f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Implementation](<https://github.com/muzairkhattak/ViFi-CLIP>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### GDT

Top-1 Acc: 92.5. Result ID: 69a1402d35dfcabb00e5c797.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0a1.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"Audioset","Backbone":"R(2+1)D","Param":"14.4M","Res":"224","Frames":"32","Modality":"V+A"}. This record does not assert independent reproduction.

### GDT

Top-1 Acc: 92.5. Result ID: 69a1402d35dfcabb00e5c810.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b161e209131cea2c0a1.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"Audioset","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"224","Frames":"32","Modality":"V+A"}. This record does not assert independent reproduction.

### MVP-shot

Top-1 Acc: 92.2. Result ID: 6a17ede4fbc373592c114799.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77471e209131cea72349.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-based CLIP","Few-shot Setting":"5-way 1-shot"}. This record does not assert independent reproduction.

### CVRL

Top-1 Acc: 92.1. Result ID: 69a1402d35dfcabb00e5c7a7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ac1e209131cea23437.md>)

[Implementation](<https://github.com/tensorflow/models/tree/master/official/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"R3D-50","Param":"36.1M","Res":"224","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### X-CLIP

Top-1 Acc: 92. Result ID: 69955f273badfaffe6513ea3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d331e209131cea385df.md>)

[Implementation](<https://www.sota2.com/aka.ms/X-CLIP>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetuning","Intermediate Dataset":"None"}. This record does not assert independent reproduction.

### ActionCLIP

Top-1 Acc: 91.4. Result ID: 699084843a6c314849011f4b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6aca1e209131cea2a40f.md>)

[Implementation](<https://github.com/sallymmx/ActionCLIP.git>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Adapting pre-trained image VL models"}. This record does not assert independent reproduction.

### XCLIP

Top-1 Acc: 91.4. Result ID: 699084843a6c314849011f4f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d331e209131cea385df.md>)

[Implementation](<https://www.sota2.com/aka.ms/X-CLIP>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Adapting pre-trained image VL models"}. This record does not assert independent reproduction.

### MIL-NCE

Top-1 Acc: 91.3. Result ID: 69a1402d35dfcabb00e5c7b5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac99.md>)

[Implementation](<https://www.di.ens.fr/willow/research/mil-nce/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"HTM","Backbone":"S3D","Param":"8.8M","Res":"224","Frames":"32","Modality":"V+T"}. This record does not assert independent reproduction.

### MIL-NCE

Top-1 Acc: 91.3. Result ID: 69a1402d35dfcabb00e5c81e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac99.md>)

[Implementation](<https://www.di.ens.fr/willow/research/mil-nce/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"HTM","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"224","Frames":"32","Modality":"V+T"}. This record does not assert independent reproduction.

### CLIP-FSAR

Top-1 Acc: 91.3. Result ID: 6a17ede4fbc373592c114798.

[Reporting paper](<https://www.sota2.com/research/paper/68fa7a8c1e209131cea83d8c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa755f1e209131cea67965.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-based CLIP","Few-shot Setting":"5-way 1-shot"}. This record does not assert independent reproduction.

### CoCLR †

Top-1 Acc: 90.6. Result ID: 69a1402d35dfcabb00e5c7b2.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"S3D","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### CoCLR †

Top-1 Acc: 90.6. Result ID: 69a1402d35dfcabb00e5c81b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"K-400","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### CLIP image-FT

Top-1 Acc: 90.5. Result ID: 699084843a6c314849011f57.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### ViCC-R+F

Top-1 Acc: 90.5. Result ID: 69a1402d35dfcabb00e5c7bc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"S3D","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-R+F

Top-1 Acc: 90.5. Result ID: 69a1402d35dfcabb00e5c824.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### ViFi-CLIP

Top-1 Acc: 90. Result ID: 699084843a6c314849011f5e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Implementation](<https://github.com/muzairkhattak/ViFi-CLIP>)

Recorded evaluation configuration: {"K":8,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### A5

Top-1 Acc: 89.9. Result ID: 699084843a6c314849011f53.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d041e209131cea375a1.md>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Adapting pre-trained image VL models"}. This record does not assert independent reproduction.

### FiT

Top-1 Acc: 89.6. Result ID: 69a149c335dfcabb00e6077a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbd1e209131cea3bbb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6c8b1e209131cea349cb.md>)

[Implementation](<https://m-bain.github.io/webvid-dataset/>)

Recorded evaluation configuration: {"Evaluation Protocol":"linear probing"}. This record does not assert independent reproduction.

### MotionFit

Top-1 Acc: 88.9. Result ID: 69a1402d35dfcabb00e5c794.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69ea1e209131cea24dd7.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"R(2+1)D","Param":"14.4M","Res":"112","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-R+F

Top-1 Acc: 88.8. Result ID: 69a1402d35dfcabb00e5c79b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"R(2+1)D","Param":"14.4M","Res":"128","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-R+F

Top-1 Acc: 88.8. Result ID: 69a1402d35dfcabb00e5c814.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"128","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### CLIP text-FT

Top-1 Acc: 88.1. Result ID: 699084843a6c314849011f5b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

Recorded evaluation configuration: {"K":16,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### UMT

Top-1 Acc: 88. Result ID: 69955f273badfaffe6513eaa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72711e209131cea5652b.md>)

[Implementation](<https://github.com/OpenGVLab/unmasked_teacher>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear Probing","Intermediate Dataset":"K700 \[8\]"}. This record does not assert independent reproduction.

### SeLaVi

Top-1 Acc: 87.7. Result ID: 69a1402d35dfcabb00e5c796.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69761e209131cea223c4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"VGG-sound","Backbone":"R(2+1)D","Param":"14.4M","Res":"112","Frames":"30","Modality":"V+A"}. This record does not assert independent reproduction.

### SeLaVi

Top-1 Acc: 87.7. Result ID: 69a1402d35dfcabb00e5c80f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69761e209131cea223c4.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"VGG-sound","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"112","Frames":"30","Modality":"V+A"}. This record does not assert independent reproduction.

### CoCLR †

Top-1 Acc: 87.3. Result ID: 69a1402d35dfcabb00e5c7b0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"S3D","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### CoCLR †

Top-1 Acc: 87.3. Result ID: 69a1402d35dfcabb00e5c819.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### Pace Pred

Top-1 Acc: 87.1. Result ID: 69a1402d35dfcabb00e5c7ac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68451e209131cea1aed0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"S3D-G","Param":"9.6M","Res":"224","Frames":"64","Modality":"V"}. This record does not assert independent reproduction.

### Pace Pred

Top-1 Acc: 87.1. Result ID: 69a1402d35dfcabb00e5c815.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68451e209131cea1aed0.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"S3D-G","Number of Parameters":"9.6M","Resolution":"224","Frames":"64","Modality":"V"}. This record does not assert independent reproduction.

### XDC

Top-1 Acc: 86.8. Result ID: 69a1402d35dfcabb00e5c795.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a21e209131cea1d485.md>)

[Implementation](<http://humamalwassel.com/publication/xdc>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"R(2+1)D","Param":"14.4M","Res":"224","Frames":"32","Modality":"V+A"}. This record does not assert independent reproduction.

### XDC

Top-1 Acc: 86.8. Result ID: 69a1402d35dfcabb00e5c80e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68a21e209131cea1d485.md>)

[Implementation](<http://humamalwassel.com/publication/xdc>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"K-400","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"224","Frames":"32","Modality":"V+A"}. This record does not assert independent reproduction.

### ViCLIP

Top-1 Acc: 86.7. Result ID: 69955f273badfaffe6513ea8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71ba1e209131cea52cd9.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear Probing","Intermediate Dataset":"Intervid-10M \[84\]"}. This record does not assert independent reproduction.

### CLIP text-FT

Top-1 Acc: 85.8. Result ID: 699084843a6c314849011f5a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

Recorded evaluation configuration: {"K":8,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### A5

Top-1 Acc: 85.7. Result ID: 699084843a6c314849011f52.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d041e209131cea375a1.md>)

Recorded evaluation configuration: {"K":8,"Adaptation strategy":"Adapting pre-trained image VL models"}. This record does not assert independent reproduction.

### ViCC-R+F

Top-1 Acc: 85.7. Result ID: 69a1402d35dfcabb00e5c7ab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"R3D","Param":"14.2M","Res":"128","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### MCN

Top-1 Acc: 85.4. Result ID: 699ac7025698665ec45566ce.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a991e209131cea2938c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a991e209131cea2938c.md>)

Recorded evaluation configuration: {"Backbone":"R3D","Resolution":"128","Pre-trained":"UCF101","Fine-tuning":true}. This record does not assert independent reproduction.

### CLIP image-FT

Top-1 Acc: 85.3. Result ID: 699084843a6c314849011f56.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

Recorded evaluation configuration: {"K":8,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### ViFi-CLIP

Top-1 Acc: 85.1. Result ID: 699084843a6c314849011f5d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Implementation](<https://github.com/muzairkhattak/ViFi-CLIP>)

Recorded evaluation configuration: {"K":4,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### MCN

Top-1 Acc: 84.8. Result ID: 699ac7025698665ec45566cd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a991e209131cea2938c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a991e209131cea2938c.md>)

Recorded evaluation configuration: {"Backbone":"R(2+1)D","Resolution":"128","Pre-trained":"UCF101","Fine-tuning":true}. This record does not assert independent reproduction.

### MemDPC

Top-1 Acc: 84.3. Result ID: 69a1402d35dfcabb00e5c79d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68171e209131cea1a215.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"R2D3D","Param":"14.2M","Res":"224","Frames":"40","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-RGB

Top-1 Acc: 84.3. Result ID: 69a1402d35dfcabb00e5c7ba.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"S3D","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-RGB

Top-1 Acc: 84.3. Result ID: 69a1402d35dfcabb00e5c822.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### X-Florence

Top-1 Acc: 84. Result ID: 699082bd3a6c3148490116a0.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee71e209131cea42c8a.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d331e209131cea385df.md>)

[Implementation](<https://www.sota2.com/aka.ms/X-CLIP>)

Recorded evaluation configuration: {"shot":"2"}. This record does not assert independent reproduction.

### SMILE

Top-1 Acc: 83.8. Result ID: 69955f273badfaffe6513eac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77b21e209131cea74d3d.md>)

[Implementation](<https://github.com/fmthoker/SMILE>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear Probing","Intermediate Dataset":"K400 \[35\]"}. This record does not assert independent reproduction.

### XCLIP

Top-1 Acc: 83.7. Result ID: 699084843a6c314849011f4e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d331e209131cea385df.md>)

[Implementation](<https://www.sota2.com/aka.ms/X-CLIP>)

Recorded evaluation configuration: {"K":8,"Adaptation strategy":"Adapting pre-trained image VL models"}. This record does not assert independent reproduction.

### iCaRL (IM)

Top-1 Acc: 83.53. Result ID: 699994ba5698665ec40859b7.

[Reporting paper](<https://www.sota2.com/research/paper/692e732fd6b0dd33429328b7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/692e732fd6b0dd33429328b7.md>)

Recorded evaluation configuration: {"Buffer Size":"2020"}. This record does not assert independent reproduction.

### TimeSformer

Top-1 Acc: 82.9. Result ID: 69a149c335dfcabb00e60779.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6dbd1e209131cea3bbb4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a1d1e209131cea25fbb.md>)

[Implementation](<https://github.com/facebookresearch/TimeSformer>)

Recorded evaluation configuration: {"Pre-training":"Sup21K","Evaluation Protocol":"linear probing"}. This record does not assert independent reproduction.

### CLIP text-FT

Top-1 Acc: 82.8. Result ID: 699084843a6c314849011f59.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6ee81e209131cea42cef.md>)

Recorded evaluation configuration: {"K":4,"Adaptation strategy":"Tuning pre-trained image VL models"}. This record does not assert independent reproduction.

### ViCC-RGB

Top-1 Acc: 82.8. Result ID: 69a1402d35dfcabb00e5c799.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"R(2+1)D","Param":"14.4M","Res":"128","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### ViCC-RGB

Top-1 Acc: 82.8. Result ID: 69a1402d35dfcabb00e5c812.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Implementation](<https://github.com/martinetoering/ViCC>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"128","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### MIL-NCE

Top-1 Acc: 82.7. Result ID: 69a1402d35dfcabb00e5c7b4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac99.md>)

[Implementation](<https://www.di.ens.fr/willow/research/mil-nce/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear","Pre-train Dataset":"HTM","Backbone":"S3D","Param":"8.8M","Res":"224","Frames":"32","Modality":"V+T"}. This record does not assert independent reproduction.

### MIL-NCE

Top-1 Acc: 82.7. Result ID: 69a1402d35dfcabb00e5c81d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa68351e209131cea1ac99.md>)

[Implementation](<https://www.di.ens.fr/willow/research/mil-nce/>)

Recorded evaluation configuration: {"Evaluation Protocol":"Linear","Pretrain Dataset":"HTM","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"224","Frames":"32","Modality":"V+T"}. This record does not assert independent reproduction.

### RTT

Top-1 Acc: 81.6. Result ID: 69a1402d35dfcabb00e5c792.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19e2f.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"R(2+1)D","Param":"14.4M","Res":"112","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### RTT

Top-1 Acc: 81.6. Result ID: 69a1402d35dfcabb00e5c80c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680d1e209131cea19e2f.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"R(2+1)D","Number of Parameters":"14.4M","Resolution":"112","Frames":"16","Modality":"V"}. This record does not assert independent reproduction.

### CoCLR

Top-1 Acc: 81.4. Result ID: 699ac7025698665ec45566cc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6a991e209131cea2938c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Backbone":"S3D","Resolution":"128","Pre-trained":"UCF101","Fine-tuning":true}. This record does not assert independent reproduction.

### CoCLR

Top-1 Acc: 81.4. Result ID: 69a1402d35dfcabb00e5c7ae.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"UCF101","Backbone":"S3D","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### CoCLR

Top-1 Acc: 81.4. Result ID: 69a1402d35dfcabb00e5c817.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa690d1e209131cea1fcba.md>)

[Implementation](<https://github.com/TengdaHan/CoCLR>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pretrain Dataset":"UCF101","Backbone":"S3D","Number of Parameters":"8.8M","Resolution":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

### SpeedNet

Top-1 Acc: 81.1. Result ID: 69a1402d35dfcabb00e5c7b3.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6b0d1e209131cea2bbe2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa680e1e209131cea19edc.md>)

Recorded evaluation configuration: {"Evaluation Protocol":"Finetune","Pre-train Dataset":"K-400","Backbone":"S3D-G","Param":"8.8M","Res":"128","Frames":"32","Modality":"V"}. This record does not assert independent reproduction.

Page 1 of 3. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/sota/video-action-recognition-on-ucf101.md?metric=Top-1%20Acc&page=2>): Follow this link to discover more pages.
