Related papers: Cognitive Disentanglement for Referring Multi-Obje…
Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference,…
Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance. This paper first studies the…
Benefiting from its ability to efficiently learn how an object is changing, correlation filters have recently demonstrated excellent performance for rapidly tracking objects. Designing effective features and handling model drifts are two…
We propose an end-to-end approach to the natural language object retrieval task, which localizes an object within an image according to a natural language description, i.e., referring expression. Previous works divide this problem into two…
Advanced in-cabin sensing technologies, especially vision based approaches, have tremendously progressed user interaction inside the vehicle, paving the way for new applications of natural user interaction. Just as humans use multiple modes…
Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make…
Cross-modal learning has become a fundamental paradigm for integrating heterogeneous information sources such as images, text, and structured attributes. However, multimodal representations often suffer from modality dominance, redundant…
Multi-object tracking (MOT) is an important and practical task related to both surveillance systems and moving camera applications, such as autonomous driving and robotic vision. However, due to unreliable detection, occlusion and fast…
Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based tracking algorithms heavily depend on spatial appearance cues such as color and…
Cross-domain Recommendation systems leverage multi-domain user interactions to improve performance, especially in sparse data or new user scenarios. However, CDR faces challenges such as effectively capturing user preferences and avoiding…
Personalized image generation has emerged as a promising direction in multimodal content creation. It aims to synthesize images tailored to individual style preferences (e.g., color schemes, character appearances, layout) and semantic…
Contextual information at the video level has become increasingly crucial for visual object tracking. However, existing methods typically use only a few tokens to convey this information, which can lead to information loss and limit their…
In this paper, we address the problem of referring expression comprehension in videos, which is challenging due to complex expression and scene dynamics. Unlike previous methods which solve the problem in multiple stages (i.e., tracking,…
Large Vision-Language Models (LVLMs) bridge the gap between visual and linguistic modalities, demonstrating strong potential across a variety of domains. However, despite significant progress, LVLMs still suffer from severe hallucination…
Recognizing objects from simultaneously sensed photometric (RGB) and depth channels is a fundamental yet practical problem in many machine vision applications such as robot grasping and autonomous driving. In this paper, we address this…
Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to…
The fusion of Large Language Models with vision models is pioneering new possibilities in user-interactive vision-language tasks. A notable application is reasoning segmentation, where models generate pixel-level segmentation masks by…
Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap…
Existing image-text matching approaches typically infer the similarity of an image-text pair by capturing and aggregating the affinities between the text and each independent object of the image. However, they ignore the connections between…
Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…