VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
cs.CV, cs.AI
Submitted: 2026-02-08
Updated: 2026-11-03
Terminology
Sources
- OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
- Qwen2.5-VL Technical Report
- Perception Encoder: The best visual embeddings are not at the output of the network
- MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems
- Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
- VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
- E5-V: Universal Embeddings with Multimodal Large Language Models
- Gemma 3 Technical Report
- Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval
- UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
- LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learning
- CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval
- VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
- video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models
- Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining
- VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation
- InternVideo: General Video Foundation Models via Generative and Discriminative Learning
- CaReBench: A Fine-Grained Benchmark for Video Captioning and Retrieval
- Kwai Keye-VL 1.5 Technical Report
- VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding
Related papers
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs
- From Formulas to Protocols: A Compositional View of Binary Target Segmentation Metrics
- Traffic Sign Recognition in Autonomous Driving: Dataset, Benchmark, and Field Experiment
- Efficient All-in-One Weather Restoration using Spectral Harmonization
- Peak-End-Net: A Peak-End Rule Inspired Framework for Generalizable Video Aesthetic Assessment