List your company

Temporal Grounding on Charades (mIoU, R@0.3, R@0.5, R@0.7)

41.85mIoUVideo-Zero
36.098837.591939.08540.5781May 14, 2026

Evaluation results

MethodLinks
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 42026.0541.8565.1140.8120.03
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=42026.0541.8565.1140.8120.03
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 32026.0541.6664.5441.419.6
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=32026.0541.6664.5441.419.6
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 52026.0541.4864.6239.9219.95
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=52026.0541.4864.6239.9219.95
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 22026.0540.8564.1939.8118.6
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=22026.0540.8564.1939.8118.6
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 12026.0538.7560.5936.9117.45
Video-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=12026.0538.7560.5936.9117.45
VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 42026.0537.5958.8236.5916.42
VisPlayBackbone=Qwen3-VL-4B-Instruct2026.0537.5958.8236.5916.42
V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 52026.0537.5558.8436.5916.29
V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 22026.0537.5359.2236.2615.94
Base ModelBackbone=Qwen3-VL-4B-Instruct, Iteration=Base2026.0537.5258.936.1216.23
Base ModelBackbone=Qwen3-VL-4B-Instruct2026.0537.5258.936.1216.23
VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 22026.0537.4958.6636.1816.37
VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 12026.0537.4658.9836.1816.51
V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 12026.0537.4658.6636.1316.69
VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 52026.0537.3558.8236.1316.26
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 42026.0537.3460.1635.5413.58
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=42026.0537.3460.1635.5413.58
VisPlayBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 32026.0537.258.0435.9116.56
V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 32026.0537.1257.9835.5116.53
V-ZeroBackbone=Qwen3-VL-4B-Instruct, Iteration=Iter 42026.0537.158.3335.2415.62
V-ZeroBackbone=Qwen3-VL-4B-Instruct2026.0537.158.3335.2415.62
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 52026.0537.0760.0334.4112.93
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=52026.0537.0760.0334.4112.93
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 32026.0536.8459.2233.613.12
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=32026.0536.8459.2233.613.12
Base ModelBackbone=Qwen3-VL-8B-Instruct, Iteration=Base2026.0536.759.1133.8713.49
VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 52026.0536.759.1134.0113.33
Base ModelBackbone=Qwen3-VL-8B-Instruct2026.0536.759.1133.8713.49
VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 22026.0536.6758.634.3513.44
VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 12026.0536.6658.9233.7113.41
V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 22026.0536.6659.1133.5213.31
V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 32026.0536.6659.1933.7613.49
VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 42026.0536.6559.0333.9213.47
VisPlayBackbone=Qwen3-VL-8B-Instruct2026.0536.6559.0333.9213.47
VisPlayBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 32026.0536.5858.7633.4413.52
V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 12026.0536.4358.4433.3313.52
V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 42026.0536.4358.6333.6613.41
V-ZeroBackbone=Qwen3-VL-8B-Instruct2026.0536.4358.6333.6613.41
V-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 52026.0536.4258.2333.4113.66
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 22026.0536.3758.8432.7712.72
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=22026.0536.3758.8432.7712.72
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=Iter 12026.0536.3258.5832.9312.82
Video-ZeroBackbone=Qwen3-VL-8B-Instruct, Iteration=12026.0536.3258.5832.9312.82