ncTimTang / AKS
[CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
☆50Updated last week
Alternatives and similar repositories for AKS:
Users that are interested in AKS are comparing it to the libraries listed below
- The official repository for paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".☆35Updated 2 months ago
- [CVPR 2025] LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding☆41Updated last month
- [ECCV 2024] ControlCap: Controllable Region-level Captioning☆74Updated 5 months ago
- Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models☆101Updated 3 weeks ago
- (CVPR 2025) PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction☆89Updated last month
- ☆60Updated 3 weeks ago
- A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability☆90Updated 4 months ago
- ☆25Updated last week
- p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay☆35Updated 3 months ago
- [NeurIPS 2024] Visual Perception by Large Language Model’s Weights☆43Updated 2 weeks ago
- [ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLM☆70Updated 5 months ago
- Official repo for "Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge" ICLR2025☆42Updated last month
- [ICLR 2025] TimeSuite: Improving MLLMs for Long Video Understanding via Grounded Tuning☆31Updated last week
- Official implementation of paper ReTaKe: Reducing Temporal and Knowledge Redundancy for Long Video Understanding☆30Updated last month
- FreeVA: Offline MLLM as Training-Free Video Assistant☆58Updated 10 months ago
- [CVPR 2025 Oral] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection☆72Updated last week
- [NeurIPS2024] Repo for the paper `ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models'☆158Updated 2 months ago
- VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning☆91Updated this week
- [CVPR'2025] VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".☆151Updated last month
- TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning☆34Updated this week
- [CVPR 2024] Context-Guided Spatio-Temporal Video Grounding☆52Updated 9 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆78Updated last week
- Official PyTorch code of GroundVQA (CVPR'24)☆59Updated 7 months ago
- [ECCV24] VISA: Reasoning Video Object Segmentation via Large Language Model☆15Updated 8 months ago
- Offical repo for CAT-V - Caption Anything in Video: Object-centric Dense Video Captioning with Spatiotemporal Multimodal Prompting☆29Updated last week
- Official implementation of "InstructSeg: Unifying Instructed Visual Segmentation with Multi-modal Large Language Models"☆35Updated 2 months ago
- [NeurlPS 2024] One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos☆113Updated 3 months ago
- 👾 E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024)☆57Updated 2 months ago
- ☆92Updated 8 months ago
- [CVPR2025] Code Release of F-LMM: Grounding Frozen Large Multimodal Models☆83Updated 8 months ago