Qingsong Zhao

Yansong Shi, Qingsong Zhao, Tianxiang Jiang et al.

The rapid advancement of multimodal large language models has demonstrated impressive capabilities, yet nearly all operate in an offline paradigm, hindering real-time interactivity. Addressing this gap, we introduce the Real-tIme Video intERaction Bench (RIVER Bench), designed for evaluating online video comprehension. RIVER Bench introduces a novel framework comprising Retrospective Memory, Live-Perception, and Proactive Anticipation tasks, closely mimicking interactive dialogues rather than responding to entire videos at once. We conducted detailed annotations using videos from diverse sources and varying lengths, and precisely defined the real-time interactive format. Evaluations across various model categories reveal that while offline models perform well in single question-answering tasks, they struggle with real-time processing. Addressing the limitations of existing models in online video interaction, especially their deficiencies in long-term memory and future perception, we proposed a general improvement method that enables models to interact with users more flexibly in real time. We believe this work will significantly advance the development of real-time interactive video understanding models and inspire future research in this emerging field. Datasets and code are publicly available at https://github.com/OpenGVLab/RIVER.

Qingsong Zhao, Yi Wang, Shuguang Dou et al.

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative pairs for contrastive learning or posing tighter class separating margins. These methods do not exploit the similarity between different classes as they adhere to i.i.d. assumption in data. In this paper, we embrace the real-world data distribution setting that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty. As the gradient of the proposed method is roughly proportional to the uncertainty of the predicted likelihoods, we name it adaptive discriminative regularization (ADR), trained along with a standard cross entropy loss in classification. Extensive experiments demonstrate that it can yield consistent and non-trivial performance improvements in a variety of visual classification tasks (over 10 benchmarks). Furthermore, we find it is robust to long-tailed and noisy label data distribution. Its flexible design enables its compatibility with mainstream classification architectures and losses.

Shuguang Dou, Xinyang Jiang, Qingsong Zhao et al.

Recently privacy concerns of person re-identification (ReID) raise more and more attention and preserving the privacy of the pedestrian images used by ReID methods become essential. De-identification (DeID) methods alleviate privacy issues by removing the identity-related of the ReID data. However, most of the existing DeID methods tend to remove all personal identity-related information and compromise the usability of de-identified data on the ReID task. In this paper, we aim to develop a technique that can achieve a good trade-off between privacy protection and data usability for person ReID. To achieve this, we propose a novel de-identification method designed explicitly for person ReID, named Person Identify Shift (PIS). PIS removes the absolute identity in a pedestrian image while preserving the identity relationship between image pairs. By exploiting the interpolation property of variational auto-encoder, PIS shifts each pedestrian image from the current identity to another with a new identity, resulting in images still preserving the relative identities. Experimental results show that our method has a better trade-off between privacy-preserving and model performance than existing de-identification methods and can defend against human and model attacks for data privacy.

Rui Yu, Runkai Zhao, Jiagen Li et al.

The LiDAR-based 3D object detector that strikes a balance between accuracy and speed is crucial for achieving real-time perception in autonomous driving and robotic navigation systems. To enhance the accuracy of point cloud detection, integrating global context for visual understanding improves the point clouds ability to grasp overall spatial information. However, many existing LiDAR detection models depend on intricate feature transformation and extraction processes, leading to poor real-time performance and high resource consumption, which limits their practical effectiveness. In this work, we propose a Faster LiDAR 3D object detection framework, called FASD, which implements heterogeneous model distillation by adaptively uniform cross-model voxel features. We aim to distill the transformer's capacity for high-performance sequence modeling into Mamba models with low FLOPs, achieving a significant improvement in accuracy through knowledge transfer. Specifically, Dynamic Voxel Group and Adaptive Attention strategies are integrated into the sparse backbone, creating a robust teacher model with scale-adaptive attention for effective global visual context modeling. Following feature alignment with the Adapter, we transfer knowledge from the Transformer to the Mamba through latent space feature supervision and span-head distillation, resulting in improved performance and an efficient student model. We evaluated the framework on the Waymo and nuScenes datasets, achieving a 4x reduction in resource consumption and a 1-2\% performance improvement over the current SoTA methods.

Jiahao Nie, Yun Xing, Wenbin An et al.

Motivated by the success of the Segment Anything Model (SAM) in promptable segmentation, recent studies leverage SAM to develop training-free solutions for few-shot segmentation, which aims to predict object masks in the target image based on a few reference exemplars. These SAM-based methods typically rely on point matching between reference and target images and use the matched dense points as prompts for mask prediction. However, we observe that dense points perform poorly in Cross-Domain Few-Shot Segmentation (CD-FSS), where target images are from medical or satellite domains. We attribute this issue to large domain shifts that disrupt the point-image interactions learned by SAM, and find that point density plays a crucial role under such conditions. To address this challenge, we propose Conditional Point Sparsification (CPS), a training-free approach that adaptively guides SAM interactions for cross-domain images based on reference exemplars. Leveraging ground-truth masks, the reference images provide reliable guidance for adaptively sparsifying dense matched points, enabling more accurate segmentation results. Extensive experiments demonstrate that CPS outperforms existing training-free SAM-based methods across diverse CD-FSS datasets.

Shuguang Dou, Xiangyang Jiang, Yuanpeng Tu et al.

The paper introduces the Decouple Re-identificatiOn and human Parsing (DROP) method for occluded person re-identification (ReID). Unlike mainstream approaches using global features for simultaneous multi-task learning of ReID and human parsing, or relying on semantic information for attention guidance, DROP argues that the inferior performance of the former is due to distinct granularity requirements for ReID and human parsing features. ReID focuses on instance part-level differences between pedestrian parts, while human parsing centers on semantic spatial context, reflecting the internal structure of the human body. To address this, DROP decouples features for ReID and human parsing, proposing detail-preserving upsampling to combine varying resolution feature maps. Parsing-specific features for human parsing are decoupled, and human position information is exclusively added to the human parsing branch. In the ReID branch, a part-aware compactness loss is introduced to enhance instance-level part differences. Experimental results highlight the efficacy of DROP, especially achieving a Rank-1 accuracy of 76.8% on Occluded-Duke, surpassing two mainstream methods. The codebase is accessible at https://github.com/shuguang-52/DROP.

Yicheng Xu, Yue Wu, Jiashuo Yu et al.

Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video publications, ExpVid features a new three-level task hierarchy that mirrors the scientific process: (1) Fine-grained Perception of tools, materials, and actions; (2) Procedural Understanding of step order and completeness; and (3) Scientific Reasoning that connects the full experiment to its published conclusions. Our vision-centric annotation pipeline, combining automated generation with multi-disciplinary expert validation, ensures that tasks require visual grounding. We evaluate 19 leading MLLMs on ExpVid and find that while they excel at coarse-grained recognition, they struggle with disambiguating fine details, tracking state changes over time, and linking experimental procedures to scientific outcomes. Our results reveal a notable performance gap between proprietary and open-source models, particularly in high-order reasoning. ExpVid not only provides a diagnostic tool but also charts a roadmap for developing MLLMs capable of becoming trustworthy partners in scientific experimentation.

Zheyuan Gu, Qingsong Zhao, Yusong Wang et al.

Current Vision-Language Models (VLMs) for deepfake detection excel at identifying spatial artifacts but overlook a critical dimension: temporal inconsistencies in video forgeries. Adapting VLMs to reason about these dynamic cues remains a distinct challenge. To bridge this gap, we propose Forensic Answer-Questioning (FAQ), a large-scale benchmark that formulates temporal deepfake analysis as a multiple-choice task. FAQ introduces a three-level hierarchy to progressively evaluate and equip VLMs with forensic capabilities: (1) Facial Perception, testing the ability to identify static visual artifacts; (2) Temporal Deepfake Grounding, requiring the localization of dynamic forgery artifacts across frames; and (3) Forensic Reasoning, challenging models to synthesize evidence for final authenticity verdicts. We evaluate a range of VLMs on FAQ and generate a corresponding instruction-tuning set, FAQ-IT. Extensive experiments show that models fine-tuned on FAQ-IT achieve advanced performance on both in-domain and cross-dataset detection benchmarks. Ablation studies further validate the impact of our key design choices, confirming that FAQ is the driving force behind the temporal reasoning capabilities of these VLMs.

Qingsong Zhao, Yi Wang, Zhipeng Zhou et al.

Sequence ordering of word vector matters a lot to text reading, which has been proven in natural language processing (NLP). However, the rule of different sequence ordering in computer vision (CV) was not well explored, e.g., why the ``zigzag" flattening (ZF) is commonly utilized as a default option to get the image patches ordering in vision networks. Notably, when decomposing multi-scale images, the ZF could not maintain the invariance of feature point positions. To this end, we investigate the Hilbert fractal flattening (HF) as another method for sequence ordering in CV and contrast it against ZF. The HF has proven to be superior to other curves in maintaining spatial locality, when performing multi-scale transformations of dimensional space. And it can be easily plugged into most deep neural networks (DNNs). Extensive experiments demonstrate that it can yield consistent and significant performance boosts for a variety of architectures. Finally, we hope that our studies spark further research about the flattening strategy of image reading.