pengzhansun / Counterfactual-Debiasing-NetworkLinks
[ACM MM 2021] A causal perspective for compositional action recognition, providing a counterfactual debiasing inference implementation to matigate the object appearance bias in videos.
☆20Updated 3 years ago
Alternatives and similar repositories for Counterfactual-Debiasing-Network
Users that are interested in Counterfactual-Debiasing-Network are comparing it to the libraries listed below
Sorting:
- ☆192Updated 2 years ago
- Code for our CVPR 2022 Paper "Hybrid Relation Guided Set Matching for Few-shot Action Recognition".☆24Updated 2 years ago
- A curated publication list on weakly-supervised temporal action localization☆154Updated last year
- Repository for the paper "Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition"☆46Updated 3 years ago
- Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"☆88Updated last year
- Implementations of some few-shot action recognition methods.☆42Updated 4 years ago
- [ICCV 2021] Target Adaptive Context Aggregation for Video Scene Graph Generation☆58Updated 3 years ago
- Fast CUDA implementation of (differentiable) otam for PyTorch using Numba☆14Updated 4 years ago
- [CVPR2021] CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning☆60Updated 3 years ago
- Code for our CVPR 2023 paper "MoLo: Motion-augmented Long-short Contrastive Learning for Few-shot Action Recognition".☆45Updated last year
- Implementation of paper "Modeling Multi-Label Action Dependencies for Temporal Action Localization"☆52Updated 2 years ago
- ☆21Updated 4 years ago
- Official implementation of the ECCV 2022 paper "CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillati…☆37Updated 2 years ago
- [BMVC 2021] A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark☆40Updated 3 years ago
- TA2N: Two-Stage Action Alignment Network for Few-Shot Action Recognition☆14Updated last year
- [CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.☆48Updated 4 years ago
- Official implementation of "ST-HOI: A Spatial-Temporal Baseline for Human-Object Interaction Detection in Videos" (ACM ICMRW 2021)☆54Updated 2 years ago
- [CVPR 2022] A large-scale public benchmark dataset for video question-answering, especially about evidence and commonsense reasoning. The…☆71Updated 2 months ago
- [CVPR 2022 Oral] Towards Open Set Temporal Action Localization☆54Updated last year
- The official implementation of 'Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation' (CVPR 2…☆47Updated 2 years ago
- Code for CVPR22 paper: Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection.☆50Updated 2 months ago
- [ICLR 2023] Temporal Alignment Representations with Contrastive Learning☆26Updated 2 years ago
- awesome video representation learning☆15Updated 4 years ago
- [AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding☆90Updated 2 years ago
- ☆39Updated 2 years ago
- Code for Static and Dynamic Concepts for Self-supervised Video Representation Learning.☆11Updated 3 years ago
- Task-adaptive Spatial-Temporal Video Sampler for Few-shot Action Recognition☆12Updated 2 years ago
- Code for "Mining the Benefits of Two-stage and One-stage HOI Detection"☆90Updated last year
- Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021☆207Updated 3 years ago
- Code for our IJCV 2023 paper "CLIP-guided Prototype Modulating for Few-shot Action Recognition".☆68Updated last year