# Few-shot video recognition on UCF-101

Source: [Few-shot video recognition on UCF-101](<https://www.sota2.com/research/sota/few-shot-video-recognition-on-ucf-101>)

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

Data updated: 2026-02-26T06:06:53.773Z

Evaluation of Few-Shot Video Recognition performance on the UCF-101 dataset, measured using K-shot accuracy metrics.

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 | Few-shot video recognition |
| Dataset (including any stated split) | UCF-101 |
| Metric | Top-1 Acc (K=2) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 13 of 13 |
| 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 (K=2)](<https://www.sota2.com/research/sota/few-shot-video-recognition-on-ucf-101.md?metric=Top-1%20Acc%20(K%3D2)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (K=4)](<https://www.sota2.com/research/sota/few-shot-video-recognition-on-ucf-101.md?metric=Top-1%20Acc%20(K%3D4)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (K=8)](<https://www.sota2.com/research/sota/few-shot-video-recognition-on-ucf-101.md?metric=Top-1%20Acc%20(K%3D8)>): Higher is better; unit: PERCENT.

- [Top-1 Acc (K=16)](<https://www.sota2.com/research/sota/few-shot-video-recognition-on-ucf-101.md?metric=Top-1%20Acc%20(K%3D16)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Acc (K=2) | Result date | Report paper |
| --- | --- | --- | --- |
| MOTE | 88.1 | Not recorded | 68fa77771e209131cea73519 |
| Zero-ViCLIP + MSTA + Lcc | 86.1 | Not recorded | 68fa77771e209131cea73519 |
| Zero-ViCLIP + MSTA | 85.1 | Not recorded | 68fa77771e209131cea73519 |
| Zero-ViCLIP + AdaptFormer | 84.8 | Not recorded | 68fa77771e209131cea73519 |
| Zero-ViCLIP + LORA | 83.5 | Not recorded | 68fa77771e209131cea73519 |
| OST | 83 | Not recorded | 68fa77771e209131cea73519 |
| ViCLIP | 83 | Not recorded | 68fa77771e209131cea73519 |
| Vanilla CLIP | 81.8 | Not recorded | 68fa77771e209131cea73519 |
| ViFi-CLIP | 80.5 | Not recorded | 68fa77771e209131cea73519 |
| A5 | 71.7 | Not recorded | 68fa77771e209131cea73519 |
| Zero-ViCLIP | 71 | Not recorded | 68fa77771e209131cea73519 |
| Vanilla CLIP | 62.8 | Not recorded | 68fa77771e209131cea73519 |
| XCLIP | 49.3 | Not recorded | 68fa77771e209131cea73519 |

### MOTE

Top-1 Acc (K=2): 88.1. Result ID: 699493cb3a6c3148491e212e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75311e209131cea6647e.md>)

[Implementation](<https://github.com/ZMHH-H/MoTE>)

Recorded evaluation configuration: {"GFLOPs":"141","Transfer learning protocol":"Tuning pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Zero-ViCLIP + MSTA + Lcc

Top-1 Acc (K=2): 86.1. Result ID: 699493cb3a6c3148491e2134.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Implementation](<https://github.com/chenhaoxing/ETL4Video>)

Recorded evaluation configuration: {"GFLOPs":"179.84","Transfer learning protocol":"Efficient transfer pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Zero-ViCLIP + MSTA

Top-1 Acc (K=2): 85.1. Result ID: 699493cb3a6c3148491e2133.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Implementation](<https://github.com/chenhaoxing/ETL4Video>)

Recorded evaluation configuration: {"GFLOPs":"179.84","Transfer learning protocol":"Efficient transfer pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Zero-ViCLIP + AdaptFormer

Top-1 Acc (K=2): 84.8. Result ID: 699493cb3a6c3148491e2131.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

Recorded evaluation configuration: {"GFLOPs":"179.80","Transfer learning protocol":"Efficient transfer pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Zero-ViCLIP + LORA

Top-1 Acc (K=2): 83.5. Result ID: 699493cb3a6c3148491e2132.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

Recorded evaluation configuration: {"GFLOPs":"179.80","Transfer learning protocol":"Efficient transfer pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### OST

Top-1 Acc (K=2): 83. Result ID: 699493cb3a6c3148491e212d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c2f.md>)

[Implementation](<https://tomchen-ctj.github.io/OST>)

Recorded evaluation configuration: {"Transfer learning protocol":"Tuning pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### ViCLIP

Top-1 Acc (K=2): 83. Result ID: 699493cb3a6c3148491e212f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

Recorded evaluation configuration: {"GFLOPs":"161","Transfer learning protocol":"Tuning pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Vanilla CLIP

Top-1 Acc (K=2): 81.8. Result ID: 699493cb3a6c3148491e212b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

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

Recorded evaluation configuration: {"GFLOPs":"282","Transfer learning protocol":"Tuning pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### ViFi-CLIP

Top-1 Acc (K=2): 80.5. Result ID: 699493cb3a6c3148491e212c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

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

Recorded evaluation configuration: {"GFLOPs":"281","Transfer learning protocol":"Tuning pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### A5

Top-1 Acc (K=2): 71.7. Result ID: 699493cb3a6c3148491e212a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

Recorded evaluation configuration: {"GFLOPs":"284","Transfer learning protocol":"Adapting pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Zero-ViCLIP

Top-1 Acc (K=2): 71. Result ID: 699493cb3a6c3148491e2130.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

Recorded evaluation configuration: {"GFLOPs":"161","Transfer learning protocol":"Efficient transfer pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### Vanilla CLIP

Top-1 Acc (K=2): 62.8. Result ID: 699493cb3a6c3148491e2128.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

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

Recorded evaluation configuration: {"GFLOPs":"281","Transfer learning protocol":"Zero-shot pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

### XCLIP

Top-1 Acc (K=2): 49.3. Result ID: 699493cb3a6c3148491e2129.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77771e209131cea73519.md>)

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

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

Recorded evaluation configuration: {"GFLOPs":"145","Transfer learning protocol":"Adapting pre-trained models","Multi-view inference":"true"}. This record does not assert independent reproduction.

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