Related papers: Combating Visual Neglect and Semantic Drift in Lar…
Video Moment Retrieval (VMR) aims to retrieve temporal segments in untrimmed videos corresponding to a given language query by constructing cross-modal alignment strategies. However, these existing strategies are often sub-optimal since…
Large Vision and Language Models (LVLMs) have shown strong performance across various vision-language tasks in natural image domains. However, their application to remote sensing (RS) remains underexplored due to significant domain…
Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR.…
Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in…
Sequential Recommender Systems (SRS) aim to predict users' next interaction based on their historical behaviors, while still facing the challenge of data sparsity. With the rapid advancement of Multimodal Large Language Models (MLLMs),…
Machine Learning (ML) is continuously permeating a growing amount of application domains. Generative AI such as Large Language Models (LLMs) also sees broad adoption to process multi-modal data such as text, images, audio, and video. While…
Although multimodal large language models (MLLMs) excel in high-level vision-language reasoning, they lack inherent awareness of visual saliency, making it difficult to identify key visual elements. To bridge this gap, we propose…
Due to the lack of extensive precisely-annotated multi-label data in real word, semi-supervised multi-label learning (SSMLL) has gradually gained attention. Abundant knowledge embedded in vision-language models (VLMs) pre-trained on…
Video semantic search in densely crowded scenes remains a challenging task due to visual encoders tendency to prioritize salient foreground regions while neglecting contextually important, background areas. We propose an Inverse Attention…
We introduce MUSE-VL, a Unified Vision-Language Model through Semantic discrete Encoding for multimodal understanding and generation. Recently, the research community has begun exploring unified models for visual generation and…
Although most existing multi-modal salient object detection (SOD) methods demonstrate effectiveness through training models from scratch, the limited multi-modal data hinders these methods from reaching optimality. In this paper, we propose…
Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to its various applications in public security and video…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities by integrating visual and textual inputs, yet modality alignment remains one of the most challenging aspects. Current MLLMs typically rely on simple adapter…
Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated forget sets. Moreover, these methods perform unlearning at a…
Recent advances in vision-language models have significantly expanded the frontiers of automated image analysis. However, applying these models in safety-critical contexts remains challenging due to the complex relationships between…
In computational pathology, few-shot whole slide image classification is primarily driven by the extreme scarcity of expert-labeled slides. Recent vision-language methods incorporate textual semantics generated by large language models, but…
It is widely agreed that open-vocabulary-based approaches outperform classical closed-set training solutions for recognizing unseen objects in images for semantic segmentation. Existing open-vocabulary approaches leverage vision-language…
Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can significantly enhance continual learning of image classes.…
In vision-language pre-training (VLP), masked image modeling (MIM) has recently been introduced for fine-grained cross-modal alignment. However, in most existing methods, the reconstruction targets for MIM lack high-level semantics, and…
Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similarities would be preserved. The triplet loss with…