Fuse To Align: Multimodal Representation Learning for Retrieval via Hypergraph Regularization
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/ispamm/GRAM
Terminology
Sources
- EVA-CLIP: Improved Training Techniques for CLIP at Scale
- TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale
- InternVideo: General Video Foundation Models via Generative and Discriminative Learning
- Link Prediction with Relational Hypergraphs
- Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos
- FLARE: Full-Modality Long-Video Audiovisual Retrieval Benchmark with User-Simulated Queries
- VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs