6 citations · 10 across the 12 of their papers we have counts for
12 papers
T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval
Yili Li, Gang Xiong, Gaopeng Gou +4
Text-to-video retrieval essentially aims to train models to align visual content with textual descriptions accurately. Due to the impressive general multimodal knowledge demonstrat…
Missing Target-Relevant Information Prediction with World Model for Accurate Zero-Shot Composed Image Retrieval
Yuanmin Tang, Jing Yu, Keke Gai +4
Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent across domain, scene, object, and attribute. The key cha…
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
Xiangyan Qu, Jing Yu, Jiamin Zhuang +3
Zero-shot learning (ZSL) aims to train a model on seen classes and recognize unseen classes by knowledge transfer through shared auxiliary information. Recent studies reveal that d…
ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
Xiangyan Qu, Gaopeng Gou, Jiamin Zhuang +5
Vision-language models (VLMs) have made significant progress in image classification by training with large-scale paired image-text data. Their performances largely depend on the p…
Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval
Yuanmin Tang, Xiaoting Qin, Jue Zhang +7
Composed Image Retrieval (CIR) aims to retrieve target images that closely resemble a reference image while integrating user-specified textual modifications, thereby capturing user…
Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval
Yuanmin Tang, Jing Yu, Keke Gai +4
Zero-Shot Composed Image Retrieval (ZS-CIR) supports diverse tasks with a broad range of visual content manipulation intentions that can be related to domain, scene, object, and at…
T2VIndexer: A Generative Video Indexer for Efficient Text-Video Retrieval
Yili Li, Jing Yu, Keke Gai +3
Current text-video retrieval methods mainly rely on cross-modal matching between queries and videos to calculate their similarity scores, which are then sorted to obtain retrieval…
IIU: Independent Inference Units for Knowledge-based Visual Question Answering
Yili Li, Jing Yu, Keke Gai +1
Knowledge-based visual question answering requires external knowledge beyond visible content to answer the question correctly. One limitation of existing methods is that they focus…
Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning
Xiangyan Qu, Jing Yu, Keke Gai +5
Recent work shows that documents from encyclopedias serve as helpful auxiliary information for zero-shot learning. Existing methods align the entire semantics of a document with co…
Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service
Yuanmin Tang, Jing Yu, Keke Gai +4
Recent advances in vision-language pre-trained models (VLPs) have significantly increased visual understanding and cross-modal analysis capabilities. Companies have emerged to prov…
Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search
Yuanmin Tang, Jing Yu, Keke Gai +4
Cross-Modal sponsored search displays multi-modal advertisements (ads) when consumers look for desired products by natural language queries in search engines. Since multi-modal ads…
Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval
Yuanmin Tang, Jing Yu, Keke Gai +4
Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks wi…