Related papers: DeMo: Decoupled Feature-Based Mixture of Experts f…

Person re-identification (ReID) aims to retrieve images of a target person from the gallery set, with wide applications in medical rehabilitation and public security. However, traditional person ReID models are typically uni-modal,…

Extracting robust discriminative features is a critical challenge in person re-identification (ReID). While Transformer-based methods have successfully addressed some limitations of convolutional neural networks (CNNs), such as their local…

Multi-Camera Multi-Object Tracking (MC-MOT) utilizes information from multiple views to better handle problems with occlusion and crowded scenes. Recently, the use of graph-based approaches to solve tracking problems has become very…

The application of mixture-of-experts (MoE) is gaining popularity due to its ability to improve model's performance. In an MoE structure, the gate layer plays a significant role in distinguishing and routing input features to different…

Person re-identification (Re-ID) aims to match identities across non-overlapping camera views. Researchers have proposed many supervised Re-ID models which require quantities of cross-view pairwise labelled data. This limits their…

Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In such cases, classical methods, or even humans, are unable…

Multispectral image pairs can provide the combined information, making object detection applications more reliable and robust in the open world. To fully exploit the different modalities, we present a simple yet effective cross-modality…

Practical cloud-edge deployment of Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models for diverse modalities. While Multi-Modal Large Language Models (MLLMs) offer…

Visible-Infrared Person Re-Identification (VI-ReID) is a challenging retrieval task under complex modality changes. Existing methods usually focus on extracting discriminative visual features while ignoring the reliability and commonality…

In this paper we introduce a novel block-based regression strategy for image denoising based on edge-aware Steered-Mixture-of-Experts (SMoE) models. SMoEs provide very sparse image representations, able to model sharp edges as well as…

Based on analyzing the character of cascaded decoder architecture commonly adopted in existing DETR-like models, this paper proposes a new decoder architecture. The cascaded decoder architecture constrains object queries to update in the…

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…

Person re-identification (Re-ID) aims at retrieving an input person image from a set of images captured by multiple cameras. Although recent Re-ID methods have made great success, most of them extract features in terms of the attributes of…

Multimodal recommendation has emerged as a promising solution to alleviate the cold-start and sparsity problems in collaborative filtering by incorporating rich content information, such as product images and textual descriptions. However,…

Most existing multimodal trackers adopt uniform fusion strategies, overlooking the inherent differences between modalities. Moreover, they propagate temporal information through mixed tokens, leading to entangled and less discriminative…

Many existing multi-modality studies are based on the assumption of modality integrity. However, the problem of missing arbitrary modalities is very common in real life, and this problem is less studied, but actually important in the task…

Hybrid-distorted image restoration (HD-IR) is dedicated to restore real distorted image that is degraded by multiple distortions. Existing HD-IR approaches usually ignore the inherent interference among hybrid distortions which compromises…

Most multi-modal knowledge graph completion (MMKGC) models use one embedding scorer to do both retrieval over the full entity set and final decision making. We argue that this coupling is a core bottleneck: global high-recall search and…

In this paper, we propose multi-stage and deformable deep convolutional neural networks for object detection. This new deep learning object detection diagram has innovations in multiple aspects. In the proposed new deep architecture, a new…

We propose a novel technique for producing high-quality 3D models that match a given target object image or scan. Our method is based on retrieving an existing shape from a database of 3D models and then deforming its parts to match the…