arXiv Computer Vision
STARE: Scene Text-Aware multimodal Retrieval for Everyday objects
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
5d ago
Exploiting Textual Semantics for Robust Cross-View Object Correspondence
Cross-view object correspondence (CVOC) aims to establish associations of the same target between query and search videos captured from different viewpoints. Existing methods often rely on visual cues...
arXiv AI
1d ago
Exploiting Textual Semantics for Robust Cross-View Object Correspondence
arXiv:2611.02356v2 Announce Type: replace-cross Abstract: Cross-view object correspondence (CVOC) aims to establish associations of the same target between query and search videos captured from diffe...
arXiv AI
Jun 16
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
arXiv:2606. 15231v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex, open-world scenarios.
arXiv AI
Sep 1
WeAgent-MMSearch: Native Text-Vision Interaction for Multimodal Search Agents
WeAgent-MMSearch introduces a multimodal search agent that preserves retrieved images as persistent references, enabling the model to inspect, process, and cite them throughout a search trajectory. The system includes a harness (WeAgent-Harness), a post‑training method (FA‑GSPO) that recovers salvageable rollouts, and a new benchmark (VisTarget‑Bench) to evaluate image‑retrieval versus visual‑perception failures. Evaluation shows that agentic post‑training boosts performance by 19.22 points, allowing the model to outperform similarly sized open‑source models and compete with much larger ones.
arXiv Machine Learning
4d ago
Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis
The paper evaluates 14 state‑of‑the‑art text‑to‑video retrieval models on three major datasets using a unified framework. It finds that short, clear, and simple captions—especially those describing single actions or color attributes—yield higher recall, while complex, multi‑step events or fine‑grained scene descriptions remain difficult for all models. Attention‑driven architectures better handle temporally dependent or multi‑step queries, whereas dual‑encoder and multimodal fusion models excel mainly on simpler captions, and cross‑dataset generalization improves with larger, more diverse caption sets but generative captions do not consistently boost accuracy.
arXiv Computer Vision
Oct 21
LVMem: Image-Augmented Memory for Long-Horizon Question Answering
arXiv:2610.27104v1 Announce Type: new Abstract: Reliable language-guided perception is essential for embodied agents, where questions about objects, events, and their locations must be answered from...