List your company

Vision-Language Tracking on OTB 99

76.4AUCVLTTT
52.06458.38264.771.018Apr 27, 2023Nov 6, 2023May 17, 2024Nov 26, 2024Jun 7, 2025Dec 17, 2025Jun 28, 2026

Evaluation results

MethodLinks
VLTTTReference Setting=NL+BBOX2024.0176.493.1
VLTT2023.0476.493.1
VLTTTInput Modality=Vision-language2026.0176.493.1
DecoupleTNL2023.0473.894.8
DecoupleTNL2024.1273.894.8
DecoupleTNLReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=322026.0373.894.8
SUTrackModel Scale=L, Resolution=2242024.1272.794.4
SDTrackSource=ESWA 20262026.0672.794.2
Open_VLTrackSource=-2026.0672.494.8
ADTrackSource=AAAI 20262026.0672.393.9
SemaTrackSource=TVC 20262026.0672.294.5
SeqTrackv2-B384Backbone=Base, Input Size=3842023.0471.893.4
SeqTrackv2-L384Backbone=Large, Input Size=3842023.0471.493.6
SeqTrackv2Model Scale=L, Resolution=3842024.1271.493.6
GLAD-L384Input Modality=Vision-language, Input Resolution=3842026.0171.493.2
SeqTrackv2-B256Backbone=Base, Input Size=2562023.0471.293.9
SUTrackModel Scale=L, Resolution=3842024.1271.293.1
SeqTrackv2Model Scale=B, Resolution=2562024.1271.293.9
DMTrack-384Input Modality=Vision-language, Input Resolution=3842026.0171.292.3
SeqTrackv2Real-time vs Non-real-time=Non-real-time, GPU speed (fps)=23, CPU speed (fps)=2, AGX speed (fps)=52026.0371.293.9
ABOTrackSource=JVCIR 20262026.0671.291.1
RrmTrackSource=TMM 20262026.0671.293.7
UVLTrack-LReference Setting=NL+BBOX2024.0171.192
CapsuleTNL2023.0471.192.4
CapsuleTNL2024.1271.192.4
ReasoningTrackSource=arXiv 20252026.0671.195.6
All-in-oneInput Modality=Vision-language2026.017193
ATSTrackSource=arXiv 20252026.067194.4
DUTrackSource=CVPR 20252026.0670.993.9
SUTrackModel Scale=B, Resolution=2242024.1270.893.4
MMTrackInput Modality=Vision-language2026.0170.591.8
MMTrack-384Source=TCSVT 20232026.0670.591.8
SeqTrackv2-L256Backbone=Large, Input Size=2562023.0470.391
Zhao et al.2023.0469.991.2
Zhao et al.2024.1269.991.2
TransVLTInput Modality=Vision-language2026.0169.990.6
Zhao et al.Real-time vs Non-real-time=Non-real-time, GPU speed (fps)=362026.0369.991.2
TransVLTSource=PRL 20232026.0669.991.2
SUTrackModel Scale=B, Resolution=3842024.1269.791.2
OneTracker2024.1269.791.5
OneTrackerReal-time vs Non-real-time=Non-real-time2026.0369.791.5
GLAD-B256Input Modality=Vision-language, Input Resolution=2562026.0169.692.4
CiteTrackerReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=22, CPU speed (fps)=2, AGX speed (fps)=42026.0369.685.1
GLADSource=IJCV 20262026.0669.692.4
DecoupleTNLInput Modality=Vision-language2026.0169.592.8
UVLTrack-BReference Setting=NL+BBOX2024.0169.389.9
DMTrack-256Input Modality=Vision-language, Input Resolution=2562026.0169.390.9
UVLTrack-BReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=52, CPU speed (fps)=4, AGX speed (fps)=62026.0369.389.9
ATTrackSource=MM 20242026.0669.390.3
UVLTrack-BSource=AAAI 20242026.0669.389.9
TDCLSource=ECAI 20242026.0669.190.2
Li et al.2023.046991
Li et al.2024.126991
Li et al.Input Modality=Vision-language2026.016991
TNL2K-2Reference Setting=NL+BBOX2024.016888
TNL2K-22023.046888
TNL2K-22024.126888
TNL2K-IIInput Modality=Vision-language2026.016888
TNL2k-IISource=CVPR 20212026.066888
SUTrackModel Scale=T, Resolution=2242024.1267.488.6
SUTrack-TReal-time vs Non-real-time=Real-time, GPU speed (fps)=100, CPU speed (fps)=23, AGX speed (fps)=342026.0367.488.6
Feng et al.2023.046773
Feng et al.2024.126773
QueryNLTInput Modality=Vision-language2026.0166.788.2
QueryNLTSource=CVPR 20242026.0666.788.2
SNLTReference Setting=NL+BBOX2024.0166.680.4
SNLT2023.0466.680.4
SNLT2024.1266.680.4
SNLTInput Modality=Vision-language2026.0166.684.8
SNLTReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=502026.0366.680.4
SNLTSource=CVPR 20212026.0666.684.8
OSDTSource=TCSVT 20242026.0666.286.7
Wang et al.2023.0465.889.1
Wang et al.2024.1265.889.1
JointNLTReference Setting=NL+BBOX2024.0165.385.6
JointNLT2023.0465.385.6
JointNLT2024.1265.385.6
JointNLTInput Modality=Vision-language2026.0165.385.6
JointNLTReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=39, CPU speed (fps)=3, AGX speed (fps)=52026.0365.385.6
JointNLTSource=CVPR 20232026.0665.385.6
UETrack-TReal-time vs Non-real-time=Real-time, GPU speed (fps)=221, CPU speed (fps)=83, AGX speed (fps)=772026.0364.884.7
UVLTrack-LReference Setting=NL2024.0163.583.2
UETrack-SReal-time vs Non-real-time=Real-time, GPU speed (fps)=183, CPU speed (fps)=68, AGX speed (fps)=672026.0363.181.9
UETrack-BReal-time vs Non-real-time=Real-time, GPU speed (fps)=163, CPU speed (fps)=56, AGX speed (fps)=602026.0361.379.7
RTTNLD2023.046179
RTTNLD2024.126179
RTTNLDInput Modality=Vision-language2026.016179
RTTNLDReal-time vs Non-real-time=Non-real-time, GPU speed (fps)=302026.036179
LSTMTrackSource=WACV 20202026.066179
UVLTrack-BReference Setting=NL2024.0160.179.1
JointNLTReference Setting=NL2024.0159.277.6
GTIReference Setting=NL2024.0158.173.2
GTI2023.0458.173.2
GTI2024.1258.173.2
GTIInput Modality=Vision-language2026.0158.173.2
GTISource=TCSVT 20212026.0657.173.2
TNLS2023.0455.372.3
TNLS2024.1255.372.3
TNLS-IIIReference Setting=NL+BBOX2024.015572
CTRNLTReference Setting=NL2024.015372