The paper introduces PRAISE, a test‑time adaptation framework for vision‑language model based person re‑identification. PRAISE constructs an Attribute‑Conditioned Subspace (ACS) from a bank of attribute prompts, reshaping query‑gallery affinities without requiring identity or attribute labels. Experiments on image‑to‑image and text‑to‑image ReID benchmarks show that PRAISE consistently improves retrieval performance over existing backbones and TTA baselines.
arXiv:2609.14419v1 Announce Type: cross Abstract: Person re-identification (ReID) is essential for multi-camera surveillance and tracking, yet remains difficult due to viewpoint and illumination chan...
arXiv:2606. 02242v1 Announce Type: cross Abstract: The joint optimization of image-based (I2I) and text-based (T2I) person re-identification (ReID) is hindered by modality discrepancies and conflicting training objectives, leading to suboptimal shared representations.
The joint optimization of image-based (I2I) and text-based (T2I) person re-identification (ReID) is hindered by modality discrepancies and conflicting training objectives, leading to suboptimal shared representations. While I2I ReID focuses on identity-level invariance across images of the same person, T2I ReID is driven by instance-specific textual descriptions tied to unique visual traits.
arXiv:2609.14100v1 Announce Type: cross Abstract: Fashion Image Captioning (FIC) plays a vital role in enhancing user experience and product search in e-commerce platforms. Unlike natural scene image...
ReText is a method that enhances image-based person re-identification by incorporating textual descriptions into training. The authors augment existing multi-camera datasets with captions generated by a fine‑tuned Vision‑Language Model and train the system on three tasks: Re-ID, image‑text matching, and image reconstruction guided by text. Experiments show that ReText improves generalization across unseen domains and outperforms current state‑of‑the‑art approaches on cross‑domain Re‑ID benchmarks.
arXiv:2607. 18695v1 Announce Type: cross Abstract: A popular route to interpretable zero-shot classification asks a large language model (LLM) to describe each class name and prompts CLIP with the resulting descriptors.
The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
arXiv:2607. 14125v1 Announce Type: new Abstract: Pre-trained vision-language models (VLMs) enable zero-shot image classification by computing the similarity score between an image and textual descriptions, typically formed by inserting a class label (e.
The paper demonstrates that vision‑language models (VLMs) possess a small set of attention heads, called Visual Retrieval Heads (VRHs), that are causally responsible for linking text prompts to specific image regions. By adapting head‑scoring techniques from language models, the authors identify VRHs as the heads whose attention from output prediction tokens, summed over the ground‑truth referent region, most reliably indicates causal grounding. Experiments across eleven VLMs and five referring‑expression benchmarks show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect, and that VRHs generalize across diverse visual tasks and transfer across models sharing an LLM backbone.
arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.
Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise.
CVE‑SAI is a method for e‑commerce product attribute indexing that first infers a candidate attribute from the primary image and question, then uses counterfactual visual evidence to decide whether to admit that candidate into the index. It employs Focus‑Zone Distortion to create an attribute‑specific visual‑dependence proxy and Evidence‑Guided Attention Redistribution to refine scoring, ensuring that only visually supported and risk‑controlled attributes are indexed. Experiments on Amazon Berkeley Objects demonstrate improved attribute inference, evidence localization, and controlled retrieval performance with minimal unsafe exposure.