Related papers: NEXT: Multi-Grained Mixture of Experts via Text-Mo…
Semantic ID (SID)-based recommendation is a promising paradigm for scaling sequential recommender systems, but existing methods largely follow a semantic-centric pipeline: item embeddings are learned from foundation models and discretized…
The Visible-Infrared Person Re-identification (VI ReID) aims to match visible and infrared images of the same pedestrians across non-overlapped camera views. These two input modalities contain both invariant information, such as shape, and…
The aim of multiple object tracking (MOT) is to detect all objects in a video and bind them into multiple trajectories. Generally, this process is carried out in two steps: detecting objects and associating them across frames based on…
Multimodal recommendation aims to recommend user-preferred candidates based on her/his historically interacted items and associated multimodal information. Previous studies commonly employ an embed-and-retrieve paradigm: learning user and…
Occluded person re-identification (ReID) aims to match occluded person images to holistic ones across dis-joint cameras. In this paper, we propose a novel framework by learning high-order relation and topology information for discriminative…
Cross-modal retrieval is an important functionality in modern search engines, as it increases the user experience by allowing queries and retrieved objects to pertain to different modalities. In this paper, we focus on the image-sentence…
Given a target image as query, person re-identification systems retrieve a ranked list of candidate matches on a per-camera basis. In deployed systems, a human operator scans these lists and labels sighted targets by touch or mouse-based…
Infrared and visible image fusion aims to integrate complementary multi-modal information into a single fused result. However, existing methods 1) fail to account for the degradation visible images under adverse weather conditions, thereby…
Multi-Modal Relation Extraction (MMRE) aims at identifying the relation between two entities in texts that contain visual clues. Rich visual content is valuable for the MMRE task, but existing works cannot well model finer associations…
The primary challenges in visible-infrared person re-identification arise from the differences between visible (vis) and infrared (ir) images, including inter-modal and intra-modal variations. These challenges are further complicated by…
We study the problem of object detection over scanned images of scientific documents. We consider images that contain objects of varying aspect ratios and sizes and range from coarse elements such as tables and figures to fine elements such…
Autonomous driving necessitates advanced object detection techniques that integrate information from multiple modalities to overcome the limitations associated with single-modal approaches. The challenges of aligning diverse data in early…
Person re-identification (re-ID) aims to retrieve the same person across different cameras. In practice, it still remains a challenging task due to background clutter, variations on body poses and view conditions, inaccurate bounding box…
When dealing with the task of fine-grained scene image classification, most previous works lay much emphasis on global visual features when doing multi-modal feature fusion. In other words, models are deliberately designed based on prior…
Person re-identification aims at establishing the identity of a pedestrian from a gallery that contains images of multiple people obtained from a multi-camera system. Many challenges such as occlusions, drastic lighting and pose variations…
Existing text-driven infrared and visible image fusion approaches often rely on textual information at the sentence level, which can lead to semantic noise from redundant text and fail to fully exploit the deeper semantic value of textual…
Current multi-modal object re-identification approaches based on large-scale pre-trained backbones (i.e., ViT) have displayed remarkable progress and achieved excellent performance. However, these methods usually adopt the standard full…
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic…
Despite the recent success of deep learning architectures, person re-identification (ReID) remains a challenging problem in real-word applications. Several unsupervised single-target domain adaptation (STDA) methods have recently been…
Vocabulary-free fine-grained image recognition aims to distinguish visually similar categories within a meta-class without a fixed, human-defined label set. Existing solutions for this problem are limited by either the usage of a large and…