ML Research Wiki / Benchmarks / Action Recognition / ActivityNet

ActivityNet

Action Recognition Benchmark

Performance Over Time

📊 Showing 16 results | 📏 Metric: mAP

Top Performing Models

Rank Model Paper mAP Date Code
1 Text4Vis (w/ ViT-L) Revisiting Classifier: Transferring Vision-Language Models for Video Recognition 96.90 2022-07-04 📦 whwu95/Cap4Video 📦 whwu95/text4vis 📦 whwu95/GPT4Vis 📦 whwu95/BIKE 📦 whwu95/ATM
2 BIKE Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models 96.10 2022-12-31 📦 whwu95/Cap4Video 📦 whwu95/text4vis 📦 whwu95/GPT4Vis 📦 whwu95/BIKE 📦 whwu95/ATM
3 InternVideo2-6B 📚 InternVideo2: Scaling Foundation Models for Multimodal Video Understanding 95.90 2024-03-22 📦 opengvlab/internvideo 📦 opengvlab/internvideo2
4 NSNet (w/ Swin-L) NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition 94.30 2022-07-21 -
5 TSQNet (w/ Swin-L) Temporal Saliency Query Network for Efficient Video Recognition 93.70 2022-07-21 -
6 DSANet (w/ 3D ResNet50) DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning 90.50 2021-05-25 📦 whwu95/DSANet
7 MARL (w/ SEResNeXt-152) Multi-Agent Reinforcement Learning Based Frame Sampling for Effective Untrimmed Video Recognition 90.05 2019-07-31 -
8 ListenToLook Listen to Look: Action Recognition by Previewing Audio 89.90 2019-12-10 📦 facebookresearch/Listen-to-Look
9 DSN Dynamic Sampling Networks for Efficient Action Recognition in Videos 87.90 2020-06-28 -
10 SMART SMART Frame Selection for Action Recognition 84.40 2020-12-19 -

All Papers (16)

whwu95/Cap4Video whwu95/text4vis
whwu95/Cap4Video whwu95/text4vis
opengvlab/internvideo opengvlab/internvideo2
whwu95/DSANet
facebookresearch/Listen-to-Look
qijiezhao/pseudo-3d-pytorch ZhaofanQiu/pseudo-3d-residual-networks