Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis
cs.IR, cs.CV, cs.LG, cs.MM
Submitted: 2026-03-07
Updated: 2026-10-30
Code: https://github.com/JanZahalka/dblp_survey
Project page: https://mwray.github.io/SSVR
Terminology
Sources
- MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation
- A CLIP-Hitchhiker's Guide to Long Video Retrieval
- Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment
- Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss
- Video-Text Pre-training with Learned Regions
- BiC-Net: Learning Efficient Spatio-Temporal Relation for Text-Video Retrieval
- TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval
- The State of Profanity Obfuscation in Natural Language Processing
- CLIP2TV: Align, Match and Distill for Video-Text Retrieval
- CLIP2Video: Mastering Video-Text Retrieval via Image CLIP
- Disentangled Representation Learning for Text-Video Retrieval
- Self-supervised Video Retrieval Transformer Network
- Foundation Models for Video Understanding: A Survey
- What is Wrong with Perplexity for Long-context Language Modeling?
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Related papers
- Revisiting Text Ranking in Deep Research
- GateSID: One Gate to Balance Semantic and Collaborative Signals across the Item Lifecycle
- SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
- GINGER: Spicing Up Graph-Based Vector Search
- Subtraction Gets You More: Gap-Aware Retrieval for Multimodal Multi-Hop QA
- One-Step Retrieval Framework for Real-Time Sponsored Search Ads Using Hierarchical Text Representations