Related papers: Combating Visual Neglect and Semantic Drift in Lar…

Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various…

Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, they often struggle to accurately spot and understand the…

Image-sentence retrieval has attracted extensive research attention in multimedia and computer vision due to its promising application. The key issue lies in jointly learning the visual and textual representation to accurately estimate…

Semi-supervised object detection (SSOD) aims to improve the performance and generalization of existing object detectors by utilizing limited labeled data and extensive unlabeled data. Despite many advances, recent SSOD methods are still…

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains…

Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…

Large Vision-Language Models (LVLMs) achieve strong performance on many multimodal tasks, but object hallucinations severely undermine their reliability. Most existing studies focus on the text modality, attributing hallucinations to overly…

Fully supervised salient object detection (SOD) methods have made considerable progress in performance, yet these models rely heavily on expensive pixel-wise labels. Recently, to achieve a trade-off between labeling burden and performance,…

Few-shot learning (FSL) has attracted considerable attention recently. Among existing approaches, the metric-based method aims to train an embedding network that can make similar samples close while dissimilar samples as far as possible and…

Recently, large-scale visual language pre-trained (VLP) models have demonstrated impressive performance across various downstream tasks. Motivated by these advancements, pioneering efforts have emerged in multi-label image recognition with…

Large Language Models (LLMs) have demonstrated exceptional proficiency in text understanding and embedding tasks. However, their potential in multimodal representation, particularly for item-to-item (I2I) recommendations, remains…

Multimodal Large Language Models (MLLMs) have emerged as a central focus in both industry and academia, but often suffer from biases introduced by visual and language priors, which can lead to multimodal hallucination. These biases arise…

There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient…

Cross-lingual word embeddings (CLWE) have been proven useful in many cross-lingual tasks. However, most existing approaches to learn CLWE including the ones with contextual embeddings are sense agnostic. In this work, we propose a novel…

Universal Multimodal Retrieval (UMR) seeks any-to-any search across text and vision, yet modern embedding models remain brittle when queries require latent reasoning (e.g., resolving underspecified references or matching compositional…

With the bloom of Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) that incorporate LLMs with pre-trained vision models have recently demonstrated impressive performance across diverse vision-language tasks. However,…

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Ship detection in remote sensing imagery is a critical task with wide-ranging applications, such as maritime activity monitoring, shipping logistics, and environmental studies. However, existing methods often struggle to capture…

Large Vision-Language Models (LVLMs) have demonstrated remarkable performance across a wide range of multimodal tasks. However, fine-tuning these models for domain-specific applications remains a computationally intensive challenge. This…