Group re-identification aims to match groups of people across disjoint cameras. In this task, the contextual information from neighbor individuals can be exploited for re-identifying each individual within the group as well as the entire group. However, compared with single person re-identification, it brings new challenges including group layout and group membership changes. Motivated by the observation that individuals who are close together are more likely to keep in the same group under different cameras than those who are far apart, we propose to model each group as a spatial K-nearest neighbor graph (SKNNG) and design a group context graph neural network (GCGNN) for graph representation learning. Specifically, for each node in the graph, the proposed GCGNN learns an embedding which aggregates the contextual information from neighbor nodes. We design multiple weighting kernels for neighborhood aggregation based on the graph properties including node in-degrees and spatial relationship attributes. We compute the similarity scores between node embeddings of two graphs for group member association and obtain the matching score between the two graphs by summing up the similarity scores of all linked node pairs. Experimental results on three public datasets show that our approach performs favorably against state-of-the-art methods and achieves high efficiency.

Understanding crowd motion dynamics and forecasting the future pedestrian trajectories are critical to various applications, e.g. autonomous driving and surveillance system. This task is challenging because when pedestrians plan the future paths in real crowd scenes, they will distinguish the priorities of following their predetermined destinations and responding to the motion behaviors of neighboring pedestrians. However, most of the existing methods ignore the problem of intention-interaction trade-off. In this paper, we tackle this problem by a hierarchical network, which achieves dynamically reasoning predetermined destinations and future trajectories. A novel graph structure called Intention-Interaction Graph (IIG) is designed to jointly model the self intentions and social interactions. To aggregate information in IIG, Interaction Gated Graph Attention Networks (IGGAN) consisting of a gate mechanism and an attention mechanism is proposed, thus achieving reasoning the influence degree of neighboring pedestrians and destinations. Experimental results on multiple widely used pedestrian trajectory prediction datasets, including two datasets in ETH and three datasets in UCY, demonstrate the effectiveness of the proposed model.

Multi-modal large language models (MLLMs) have made significant strides in various visual understanding tasks. However, the majority of these models are constrained to process low-resolution images, which limits their effectiveness in perception tasks that necessitate detailed visual information. In our study, we present MG-LLaVA, an innovative MLLM that enhances the model’s visual processing capabilities by incorporating a multi-granularity vision flow, which includes low-resolution, high-resolution, and object-centric features. We propose the integration of an additional high-resolution visual encoder to capture fine-grained details, which are then fused with base visual features through a Conv-Gate fusion network. To further refine the model’s object recognition abilities, we incorporate object-level features derived from bounding boxes identified by offline detectors. Being trained solely on publicly available multimodal data through instruction tuning, MG-LLaVA demonstrates exceptional perception skills. We instantiate MG-LLaVA with a wide variety of language encoders, ranging from 3.8B to 34B, to evaluate the model’s performance comprehensively. Extensive evaluations across multiple benchmarks demonstrate that MG-LLaVA outperforms existing MLLMs of comparable parameter sizes, showcasing its remarkable efficacy.

Spatial misalignment caused by variations in poses and viewpoints is one of the most critical issues that hinder the performance improvement in existing person re-identification (Re-ID) algorithms. Although it is straightforward to explore correspondence learning algorithms for alignment, online learning is intractable for negative pairs due to the intrinsic visual difference between negative pairs and efficiency concern. To address this problem, in this paper, we present a robust and efficient graph correspondence transfer (REGCT) approach for explicit spatial alignment in Re-ID. Specifically, we propose the off-line correspondence learning and on-line correspondence transfer framework. During training, patch-wise correspondences between positive training pairs are established via graph matching. By exploiting both spatial and visual contexts of human appearance in graph matching, meaningful semantic correspondences can be obtained. During testing, the off-line learned patch-wise correspondence templates are transferred to test pairs with similar pose-pair configurations for local feature distance calculation. To enhance the robustness of correspondence transfer, we design a novel pose context descriptor to accurately model human body configurations, and present an approach to measure the similarity between a pair of pose context descriptors. Meanwhile, to improve testing efficiency, we propose a correspondence template ensemble method using the voting mechanism, which significantly reduces the amount of patch-wise matchings involved in distance calculation. With aforementioned strategies, the REGCT model can effectively and efficiently handle the spatial misalignment problem in Re-ID. Extensive experiments on five challenging benchmarks, including VIPeR, Road, PRID450S, 3DPES and CUHK01, evidence the superior performance of REGCT over other state-of-the-art approaches.