facebookresearch / stepdiff
Data release for Step Differences in Instructional Video (CVPR24)
☆13Updated 10 months ago
Alternatives and similar repositories for stepdiff:
Users that are interested in stepdiff are comparing it to the libraries listed below
- Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024)☆38Updated 2 weeks ago
- Implementation of paper 'Helping Hands: An Object-Aware Ego-Centric Video Recognition Model'☆33Updated last year
- [CVPR 2024] Data and benchmark code for the EgoExoLearn dataset☆56Updated 7 months ago
- ☆61Updated last year
- This repository contains the Adverbs in Recipes (AIR) dataset and the code published at the CVPR 23 paper: "Learning Action Changes by Me…☆13Updated last year
- Code implementation for paper titled "HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision"☆26Updated last year
- [ECCV2024, Oral, Best Paper Finalist]This is the official implementation of the paper "LEGO: Learning EGOcentric Action Frame Generation …☆37Updated 2 months ago
- HT-Step is a large-scale article grounding dataset of temporal step annotations on how-to videos☆18Updated last year
- ☆9Updated 10 months ago
- ☆25Updated last year
- This repo contains source code for Glance and Focus: Memory Prompting for Multi-Event Video Question Answering (Accepted in NeurIPS 2023)☆27Updated 9 months ago
- ☆33Updated 7 months ago
- ☆23Updated 2 years ago
- [ECCV 2024] Learning Video Context as Interleaved Multimodal Sequences☆37Updated last month
- Vision Relation Transformer for Unbiased Scene Graph Generation (ICCV 2023)☆22Updated last year
- Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities (NeurIPS 2023)☆41Updated last year
- Code and data release for the paper "Learning Object State Changes in Videos: An Open-World Perspective" (CVPR 2024)☆32Updated 7 months ago
- Official code for the paper, "TaCA: Upgrading Your Visual Foundation Model with Task-agnostic Compatible Adapter".☆16Updated last year
- Official code for "Disentangling Visual Embeddings for Attributes and Objects" Published at CVPR 2022☆35Updated last year
- Video + CLIP Baseline for Ego4D Long Term Action Anticipation Challenge (CVPR 2022)☆13Updated 2 years ago
- ☆30Updated 8 months ago
- Code for the paper "Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundatio…☆29Updated last year
- Official code repo of PIN: Positional Insert Unlocks Object Localisation Abilities in VLMs☆26Updated 3 months ago
- [ICLR 2025] CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion☆41Updated 3 months ago
- [NeurIPS-24] This is the official implementation of the paper "DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effect…☆35Updated 10 months ago
- Training-free Guidance in Text-to-Video Generation via Multimodal Planning and Structured Noise Initialization☆15Updated last week
- The official PyTorch implementation of the IEEE/CVF Computer Vision and Pattern Recognition (CVPR) '24 paper PREGO: online mistake detect…☆23Updated 2 weeks ago
- [ECCV 2024] ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video☆21Updated 8 months ago
- 👾 E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024)☆57Updated 3 months ago
- (NeurIPS 2024 Spotlight) TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment☆28Updated 6 months ago