ICML 2024 accepted papers on Video
23 of the 2,610 papers accepted at ICML 2024 (0.9%) are on Video, compared with 0.6% at ICML 2023. They fall into 4 topics.
See ICML 2024 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Video generation · 8 papers
- VideoPoet: A Large Language Model for Zero-Shot Video Generation (22 citations)
- RoboDreamer: Learning Compositional World Models for Robot Imagination (4 citations)
- HumanTOMATO: Text-aligned Whole-body Motion Generation (2 citations)
- Position: Video as the New Language for Real-World Decision Making (2 citations)
- Rolling Diffusion Models (1 citation)
- Boximator: Generating Rich and Controllable Motions for Video Synthesis
- FRAG: Frequency Adapting Group for Diffusion Video Editing
- Slicedit: Zero-Shot Video Editing With Text-to-Image Diffusion Models Using Spatio-Temporal Slices
Video-language understanding · 8 papers
- VideoPrism: A Foundational Visual Encoder for Video Understanding (14 citations)
- Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization (5 citations)
- Memory Consolidation Enables Long-Context Video Understanding (3 citations)
- Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition (3 citations)
- Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning (2 citations)
- STELLA: Continual Audio-Video Pre-training with SpatioTemporal Localized Alignment
- video-SALMONN: Speech-Enhanced Audio-Visual Large Language Models
- Multi-Factor Adaptive Vision Selection for Egocentric Video Question Answering
Video segmentation and tracking · 5 papers
- Prototypical Transformer As Unified Motion Learners (8 citations)
- EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens (3 citations)
- Visual Representation Learning with Stochastic Frame Prediction (1 citation)
- EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
- Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring
Action recognition · 2 papers
- Genie: Generative Interactive Environments (12 citations)
- Taylor Videos for Action Recognition (1 citation)