ICLR 2024 accepted papers on Video
46 of the 2,259 papers accepted at ICLR 2024 (2.0%) are on Video, compared with 1.4% at ICLR 2023. They fall into 4 topics.
See ICLR 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 · 25 papers
- TokenFlow: Consistent Diffusion Features for Consistent Video Editing (42 citations)
- ControlVideo: Training-free Controllable Text-to-video Generation (34 citations)
- Human Motion Diffusion as a Generative Prior (32 citations)
- Language Model Beats Diffusion - Tokenizer is key to visual generation (22 citations)
- SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction (12 citations)
- Single Motion Diffusion (12 citations)
- FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing (10 citations)
- VDT: General-purpose Video Diffusion Transformers via Mask Modeling (9 citations)
- Seer: Language Instructed Video Prediction with Latent Diffusion Models (6 citations)
- Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (5 citations)
- OmniControl: Control Any Joint at Any Time for Human Motion Generation (5 citations)
- FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling (4 citations)
and 13 more in the interactive map.
Video segmentation and tracking · 11 papers
- Neural Rate Control for Learned Video Compression (15 citations)
- Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram (3 citations)
- FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning (1 citation)
- Progressive Fourier Neural Representation for Sequential Video Compilation (1 citation)
- Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos (1 citation)
- Towards Principled Representation Learning from Videos for Reinforcement Learning (1 citation)
- Don't Judge by the Look: Towards Motion Coherent Video Representation
- Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
- VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
- A unique M-pattern for micro-expression spotting in long videos
- Video Decomposition Prior: Editing Videos Layer by Layer
Video-language understanding · 6 papers
- InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation (32 citations)
- Multi-granularity Correspondence Learning from Long-term Noisy Videos (4 citations)
- Video Language Planning (3 citations)
- Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding (1 citation)
- Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
- ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
Action recognition · 4 papers
- AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos? (8 citations)
- Boundary Denoising for Video Activity Localization (5 citations)
- FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition (4 citations)
- Learning to Act from Actionless Videos through Dense Correspondences (1 citation)