Video Understanding papers, 2023–2026
Video recognition and understanding
Scope: NeurIPS, ICLR, ICML and CVPR, 2023–2026. 2,261 papers are tagged with this topic.
Key findings
- Video Understanding went from 319 papers in 2023 to 832 in 2026, roughly 2.6x in three years.
- CVPR publishes the most Video Understanding work: 1,037 papers from 2023 to 2026, 46% of the four-venue total.
- The fastest-growing overlap is with Diffusion Models: papers tagged with both rose from 8 in 2023 to 116 in 2026.
- Among the 5 topics under Computer Vision, it ranks #3 by 2026 paper count; the fastest grower in the group, Image Generation, is up 2.2x versus 2.6x here.
Papers per venue
Counts by year and venue
| Year | NeurIPS | ICLR | ICML | CVPR | Total |
|---|---|---|---|---|---|
| 2023 | 47 | 44 | 34 | 194 | 319 |
| 2024 | 113 | 47 | 67 | 204 | 431 |
| 2025 | 222 | 95 | 64 | 298 | 679 |
| 2026 | 229 | 148 | 114 | 341 | 832 |
Representative papers
Spread across years and venues so every edition shows up
- NeurIPS 2026Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video
- ICML 2026A Single Layer to Explain Them All: Understanding Massive Values in Large Language Models
- ICLR 2026Action-Guided Attention for Video Action Anticipation
- CVPR 20264D-RGPT Toward Region-level 4D Understanding via Perceptual Distillation
- NeurIPS 20254DGCPro: Efficient Hierarchical 4D Gaussian Compression for Progressive Volumetric Video Streaming
- ICML 2025$\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation
- ICLR 2025Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions
- CVPR 20254D-Fly: Fast 4D Reconstruction from a Single Monocular Video
- NeurIPS 2024$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
- ICML 2024Enhancing Sufficient Dimension Reduction via Hellinger Correlation
- ICLR 2024Don't Judge by the Look: Towards Motion Coherent Video Representation
- CVPR 2024Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement
- NeurIPS 2023A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship
- ICML 2023Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
- ICLR 2023A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
- CVPR 20231000 FPS HDR Video With a Spike-RGB Hybrid Camera
- NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
- ICML 2026AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
- ICLR 2026Emotions Where Art Thou: Understanding and Characterizing the Emotional Latent Space of Large Language Models
- CVPR 2026Accelerating Streaming Video Large Language Models via Hierarchical Token Compression
All Video Understanding papers
679 papers, page 11 of 14
- NeurIPS 2025FlexSelect: Flexible Token Selection for Efficient Long Video Understanding
- NeurIPS 2025Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models
- NeurIPS 2025FrameShield: Adversarially Robust Video Anomaly Detection
- NeurIPS 2025Gaze-VLM: Bridging Gaze and VLMs through Attention Regularization for Egocentric Understanding
- NeurIPS 2025GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images
- NeurIPS 2025Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
- NeurIPS 2025Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection
- NeurIPS 2025HEIR: Learning Graph-Based Motion Hierarchies
- NeurIPS 2025HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation
- NeurIPS 2025Holistic Order Prediction in Natural Scenes
- NeurIPS 2025HoliTom: Holistic Token Merging for Fast Video Large Language Models
- NeurIPS 2025HoloScene: Simulation‑Ready Interactive 3D Worlds from a Single Video
- NeurIPS 2025HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
- NeurIPS 2025iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning
- NeurIPS 2025Imagine360: Immersive 360 Video Generation from Perspective Anchor
- NeurIPS 2025Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding
- NeurIPS 2025Improving Perturbation-based Explanations by Understanding the Role of Uncertainty Calibration
- NeurIPS 2025In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting
- NeurIPS 2025InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding
- NeurIPS 2025INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning
- NeurIPS 2025Instant4D: 4D Gaussian Splatting in Minutes
- NeurIPS 2025JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation
- NeurIPS 2025LaViDa: A Large Diffusion Model for Vision-Language Understanding
- NeurIPS 2025Learning Skill-Attributes for Transferable Assessment in Video
- NeurIPS 2025Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
- NeurIPS 2025LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
- NeurIPS 2025Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding
- NeurIPS 2025LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization
- NeurIPS 2025LuxDiT: Lighting Estimation with Video Diffusion Transformer
- NeurIPS 2025Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions
- NeurIPS 2025Mitigating Semantic Collapse in Partially Relevant Video Retrieval
- NeurIPS 2025MLLMs Need 3D-Aware Representation Supervision for Scene Understanding
- NeurIPS 2025MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
- NeurIPS 2025Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
- NeurIPS 2025MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval
- NeurIPS 2025MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection
- NeurIPS 2025Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction
- NeurIPS 2025Motion4D: Learning 3D-Consistent Motion and Semantics for 4D Scene Understanding
- NeurIPS 2025MR. Video: MapReduce as an Effective Principle for Long Video Understanding
- NeurIPS 2025Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration
- NeurIPS 2025MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
- NeurIPS 2025NAUTILUS: A Large Multimodal Model for Underwater Scene Understanding
- NeurIPS 2025NEED: Cross-Subject and Cross-Task Generalization for Video and Image Reconstruction from EEG Signals
- NeurIPS 2025Neural B-frame Video Compression with Bi-directional Reference Harmonization
- NeurIPS 2025OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels
- NeurIPS 2025On the Hardness of Approximating Distributions with Tractable Probabilistic Models
- NeurIPS 2025One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding
- NeurIPS 2025One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution
- NeurIPS 2025OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
- NeurIPS 2025OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data
Ask about this trend from Claude or Cursor
Connect the Paperlist MCP and your assistant can pull the numbers on this page while you draft a survey, pick a direction or plan a submission: papers per year and venue, growth, the fastest-rising sub-themes and representative papers, shaped around your question.
Copy this prompt into your assistant
Use paperlist to show how Video Understanding papers grew at CVPR from 2023 to 2026, and which year jumped the most.
Tool the assistant calls: get_topic_stats {"topic": "video-understanding"}
Set up Paperlist MCP in two minutes (Claude Code, Cursor, Codex, ChatGPT)
FAQ
- How many Video Understanding papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?
- 2,261 in total: 319 in 2023, 431 in 2024, 679 in 2025, 832 in 2026.
- How many Video Understanding papers are at NeurIPS 2026?
- NeurIPS 2026 has 229 Video Understanding papers, versus 222 the year before.
- How many Video Understanding papers are at ICLR 2026?
- ICLR 2026 has 148 Video Understanding papers, versus 95 the year before.
- How many Video Understanding papers are at ICML 2026?
- ICML 2026 has 114 Video Understanding papers, versus 64 the year before.
- How many Video Understanding papers are at CVPR 2026?
- CVPR 2026 has 341 Video Understanding papers, versus 298 the year before.
- Which conference publishes the most Video Understanding papers?
- CVPR, with 1,037 papers from 2023 to 2026.