TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

SotA/Robots/Activity Recognition/ActivityNet

Activity Recognition on ActivityNet

Metric: mAP (higher is better)

LeaderboardDataset
Loading chart...

Results

Submit a result
#Model↕mAP▼Extra DataPaperDate↕Code
1Text4Vis (w/ ViT-L)96.9NoRevisiting Classifier: Transferring Vision-Langu...2022-07-04Code
2BIKE96.1NoBidirectional Cross-Modal Knowledge Exploration ...2022-12-31Code
3InternVideo2-6B95.9YesInternVideo2: Scaling Foundation Models for Mult...2024-03-22Code
4NSNet (w/ Swin-L)94.3NoNSNet: Non-saliency Suppression Sampler for Effi...2022-07-21-
5TSQNet (w/ Swin-L)93.7NoTemporal Saliency Query Network for Efficient Vi...2022-07-21-
6DSANet (w/ 3D ResNet50)90.5NoDSANet: Dynamic Segment Aggregation Network for ...2021-05-25Code
7MARL (w/ SEResNeXt-152)90.05NoMulti-Agent Reinforcement Learning Based Frame S...2019-07-31-
8ListenToLook89.9NoListen to Look: Action Recognition by Previewing...2019-12-10Code
9DSN87.9NoDynamic Sampling Networks for Efficient Action R...2020-06-28-
10SMART84.4NoSMART Frame Selection for Action Recognition2020-12-19-
11Ada3D84No2D or not 2D? Adaptive 3D Convolution Selection ...2020-12-29-
12RRA83.4NoFine-grained Video Categorization with Redundanc...2018-10-26-
13P3D78.9NoLearning Spatio-Temporal Representation with Pse...2017-11-28Code
14LSTM + Pretrained on YT-8M75.6NoYouTube-8M: A Large-Scale Video Classification B...2016-09-27Code
15VGG19 + 393K webcam images53.8YesDo Less and Achieve More: Training CNNs for Acti...2015-12-22-
16CD-UAR53.8NoTowards Universal Representation for Unseen Acti...2018-03-22-
17VGG1952.3NoDo Less and Achieve More: Training CNNs for Acti...2015-12-22-