dingmyu / VRDP
[NeurIPS 2021] Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language
☆45Updated last year
Related projects: ⓘ
- This repo contains the pytorch implementation for Dynamic Concept Learner (accepted by ICLR 2021).☆37Updated 2 months ago
- ☆39Updated 7 months ago
- ☆36Updated 2 years ago
- Official Repository of NeurIPS2021 paper: PTR☆33Updated 2 years ago
- ☆31Updated this week
- Official Code for Neural Systematic Binder☆28Updated last year
- Official PyTorch implementation of "Improving Generative Imagination in Object-Centric World Models"☆34Updated last year
- ACRE: Abstract Causal REasoning Beyond Covariation☆18Updated 2 years ago
- [ICLR 2022] RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning☆63Updated 2 years ago
- Learning Long-term Visual Dynamics with Region Proposal Interaction Networks (ICLR 2021)☆112Updated 2 years ago
- SNARE Dataset with MATCH and LaGOR models☆23Updated 5 months ago
- Code for Look for the Change paper published at CVPR 2022☆35Updated last year
- Code and models of MOCA (Modular Object-Centric Approach) proposed in "Factorizing Perception and Policy for Interactive Instruction Foll…☆37Updated 2 months ago
- [NeurIPS 2022] code for "Visual Concepts Tokenization"☆21Updated last year
- [NeurIPS 2021 Spotlight] Learning to Compose Visual Relations☆100Updated last year
- Official code for Slot-Transformer for Videos (STEVE)☆41Updated last year
- Code for NeurIPS 2022 Datasets and Benchmarks paper - EgoTaskQA: Understanding Human Tasks in Egocentric Videos.☆28Updated last year
- Official code for NeurRIPS 2020 paper "Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D"☆26Updated last year
- Code for ECCV 2020 paper - LEMMA: A Multi-view Dataset for LEarning Multi-agent Multi-task Activities☆27Updated 3 years ago
- [ICML 2020] Visual Grounding of Learned Physical Models☆37Updated 3 years ago
- Code release for ICLR 2023 paper: SlotFormer on object-centric dynamics models☆97Updated 11 months ago
- [Findings of EMNLP 2022] AssistSR: Task-oriented Video Segment Retrieval for Personal AI Assistant☆23Updated last year
- CRIPP-VQA Benchmark -- EMNLP, 2022☆9Updated last year
- This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes …☆82Updated last year
- [ICLR 2019] ]Unsupervised Discovery of Parts, Structure, and Dynamics☆46Updated last year
- [ICCV'21] Curious Representation Learning for Embodied Intelligence☆27Updated 2 years ago
- Learning about objects and their properties by interacting with them☆12Updated 3 years ago
- Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution☆24Updated 3 years ago
- Repo for "Physion: Evaluating Physical Prediction from Vision in Humans and Machines", presented at NeurIPS 2021 (Datasets & Benchmarks t…☆56Updated last year