PolyU-ChenLab / ETBench
πΎ E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024)
β55Updated last month
Alternatives and similar repositories for ETBench:
Users that are interested in ETBench are comparing it to the libraries listed below
- β68Updated 3 months ago
- Official implementation of HawkEye: Training Video-Text LLMs for Grounding Text in Videosβ38Updated 10 months ago
- FreeVA: Offline MLLM as Training-Free Video Assistantβ57Updated 9 months ago
- β29Updated 7 months ago
- [CVPR'25] VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selectionβ56Updated 2 weeks ago
- Official PyTorch code of GroundVQA (CVPR'24)β56Updated 6 months ago
- The official repository for paper "PruneVid: Visual Token Pruning for Efficient Video Large Language Models".β32Updated 3 weeks ago
- [CVPR 2024] Official PyTorch implementation of the paper "One For All: Video Conversation is Feasible Without Video Instruction Tuning"β31Updated last year
- [ICLR 2025] IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Modelβ27Updated 3 months ago
- TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Modelsβ28Updated 4 months ago
- [NeurIPS 2022] Embracing Consistency: A One-Stage Approach for Spatio-Temporal Video Groundingβ47Updated last year
- [ECCV 2024] Learning Video Context as Interleaved Multimodal Sequencesβ36Updated this week
- [CVPR 2024] Context-Guided Spatio-Temporal Video Groundingβ51Updated 8 months ago
- [CVPR2025] Number it: Temporal Grounding Videos like Flipping Mangaβ58Updated this week
- [ECCV 2024] Elysium: Exploring Object-level Perception in Videos via MLLMβ68Updated 4 months ago
- Egocentric Video Understanding Dataset (EVUD)β27Updated 8 months ago
- [ECCV 2024] ControlCap: Controllable Region-level Captioningβ71Updated 4 months ago
- [NeurlPS 2024] One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videosβ107Updated 2 months ago
- Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Modelsβ85Updated 2 months ago
- [ECCV2024] Official code implementation of Merlin: Empowering Multimodal LLMs with Foresight Mindsβ90Updated 8 months ago
- (NeurIPS 2024 Spotlight) TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignmentβ26Updated 5 months ago
- VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMsβ44Updated this week
- Repository of paper: Position-Enhanced Visual Instruction Tuning for Multimodal Large Language Modelsβ37Updated last year
- γNeurIPS 2024γThe official code of paper "Automated Multi-level Preference for MLLMs"β18Updated 5 months ago
- β58Updated last year
- Emerging Pixel Grounding in Large Multimodal Models Without Grounding Supervisionβ33Updated 4 months ago