LeapLabTHU / AdaFocusV2
☆88Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for AdaFocusV2
- Official Code Release for Container : Context Aggregation Network☆46Updated 3 years ago
- Reducing spatial redundancy in video recognition. SOTA computational efficiency.☆122Updated 2 years ago
- Jittor implementation of Vision Transformer with Deformable Attention☆30Updated 2 years ago
- Official implementation of Dynamic Perceiver☆41Updated 11 months ago
- Code accompanying Ego-Exo: Transferring Visual Representations from Third-person to First-person Videos (CVPR 2021)☆33Updated 3 years ago
- [IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition☆40Updated 6 months ago
- Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation, ECCV 2020 Oral☆66Updated 4 years ago
- [CVPR 2024] Data and benchmark code for the EgoExoLearn dataset☆46Updated 2 months ago
- [arXiv:2309.16669] Code release for "Training a Large Video Model on a Single Machine in a Day"☆114Updated 3 months ago
- Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)☆91Updated last year
- Official PyTorch implementation of the ECCV 2022 paper: Efficient Video Transformers with Spatial-Temporal Token Selection.☆45Updated 2 years ago
- cuda implementation of depthwise conv3d☆21Updated 3 years ago
- [CVPR 2022 (oral)] Bongard-HOI for benchmarking few-shot visual reasoning☆64Updated 2 years ago
- ☆44Updated 3 years ago
- [CVPR 2024 Champions] Solutions for EgoVis Chanllenges in CVPR 2024☆107Updated 4 months ago
- ☆57Updated last year
- [ICLR2024] Exploring Target Representations for Masked Autoencoders☆51Updated 9 months ago
- Code and model for "Multi-dataset Training of Transformers for Robust Action Recognition", NeurIPS 2022 Spotlight☆19Updated last year
- [CVPR2021] Look before you leap: learning landmark features for one-stage visual grounding.☆47Updated 3 years ago
- [arXiv] Cross-Modal Adapter for Text-Video Retrieval☆53Updated last year
- Official implement of Evo-ViT: Slow-Fast Token Evolution for Dynamic Vision Transformer☆69Updated 2 years ago
- Code for ECCV2022 Paper "Mining Cross-Person Cues for Body-Part Interactiveness Learning in HOI Detection"☆34Updated last year
- This is the official PyTorch implementation for "Mesa: A Memory-saving Training Framework for Transformers".☆118Updated 2 years ago
- Adaptive Token Sampling for Efficient Vision Transformers (ECCV 2022 Oral Presentation)☆94Updated 6 months ago
- A PyTorch implementation of the paper "Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis"☆33Updated 4 months ago
- Series of work (ECCV2020, CVPR2021, CVPR2021, ECCV2022) about Compositional Learning for Human-Object Interaction Exploration☆78Updated last year
- PyTorch implementation of the paper "MILAN: Masked Image Pretraining on Language Assisted Representation" https://arxiv.org/pdf/2208.0604…☆79Updated 2 years ago
- Implementation of paper 'Helping Hands: An Object-Aware Ego-Centric Video Recognition Model'☆31Updated last year
- ☆47Updated last year
- ☆36Updated last year