Guijian Tang

Donghua Wang, Wen Yao, Tingsong Jiang et al.

Over the past decade, deep learning has revolutionized conventional tasks that rely on hand-craft feature extraction with its strong feature learning capability, leading to substantial enhancements in traditional tasks. However, deep neural networks (DNNs) have been demonstrated to be vulnerable to adversarial examples crafted by malicious tiny noise, which is imperceptible to human observers but can make DNNs output the wrong result. Existing adversarial attacks can be categorized into digital and physical adversarial attacks. The former is designed to pursue strong attack performance in lab environments while hardly remaining effective when applied to the physical world. In contrast, the latter focus on developing physical deployable attacks, thus exhibiting more robustness in complex physical environmental conditions. Recently, with the increasing deployment of the DNN-based system in the real world, strengthening the robustness of these systems is an emergency, while exploring physical adversarial attacks exhaustively is the precondition. To this end, this paper reviews the evolution of physical adversarial attacks against DNN-based computer vision tasks, expecting to provide beneficial information for developing stronger physical adversarial attacks. Specifically, we first proposed a taxonomy to categorize the current physical adversarial attacks and grouped them. Then, we discuss the existing physical attacks and focus on the technique for improving the robustness of physical attacks under complex physical environmental conditions. Finally, we discuss the issues of the current physical adversarial attacks to be solved and give promising directions.

Songyuan Yang, Weijiang Yu, Jilin Ma et al.

Video reasoning has advanced with large multimodal models (LMMs), yet their inference is often a single pass that returns an answer without verifying whether the reasoning is evidence-aligned. We introduce Reinforce to Learn, Elect to Reason (RLER), a dual paradigm that decouples learning to produce evidence from obtaining a reliable answer. In RLER-Training, we optimize the policy with group-relative reinforcement learning (RL) and 3 novel task-driven rewards: Frame-sensitive reward grounds reasoning on explicit key frames, Think-transparency reward shapes readable and parsable reasoning traces, and Anti-repetition reward boosts information density. These signals teach the model to emit structured, machine-checkable evidence and potentiate reasoning capabilities. In RLER-Inference, we apply a train-free orchestrator that generates a small set of diverse candidates, parses their answers and cited frames, scores them by evidence consistency, confidence, transparency, and non-redundancy, and then performs a robust evidence-weighted election. This closes the loop between producing and using evidence, improving reliability and interpretability without enlarging the model. We comprehensively evaluate RLER against various open-source and RL-based LMMs on 8 representative benchmarks. RLER achieves state of the art across all benchmarks and delivers an average improvement of 6.3\% over base models, while using on average 3.1 candidates per question, indicating a favorable balance between compute and quality. The results support a simple thesis: making evidence explicit during learning and electing by evidence during inference is a robust path to trustworthy video reasoning.

Songsong Zhang, Chuanqi Tang, Hongguang Zhang et al.

Identity-Preserving Personalized Generation (IPPG) has advanced film production and artistic creation, yet existing approaches overemphasize facial regions, resulting in outputs dominated by facial close-ups.These methods suffer from weak visual narrativity and poor semantic consistency under complex text prompts, with the core limitation rooted in identity (ID) feature embeddings undermining the semantic expressiveness of generative models. To address these issues, this paper presents an IPPG method that breaks the constraint of facial close-ups, achieving synergistic optimization of identity fidelity and scene semantic creation. Specifically, we design a Dual-Line Inference (DLI) pipeline with identity-semantic separation, resolving the representation conflict between ID and semantics inherent in traditional single-path architectures. Further, we propose an Identity Adaptive Fusion (IdAF) strategy that defers ID-semantic fusion to the noise prediction stage, integrating adaptive attention fusion and noise decision masking to avoid ID embedding interference on semantics without manual masking. Finally, an Identity Aggregation Prepending (IdAP) module is introduced to aggregate ID information and replace random initializations, further enhancing identity preservation. Experimental results validate that our method achieves stable and effective performance in IPPG tasks beyond facial close-ups, enabling efficient generation without manual masking or fine-tuning. As a plug-and-play component, it can be rapidly deployed in existing IPPG frameworks, addressing the over-reliance on facial close-ups, facilitating film-level character-scene creation, and providing richer personalized generation capabilities for related domains.

Songyuan Yang, Weijiang Yu, Ziyu Liu et al.

When video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context. Appending textual or multi-clip evidence, however, forces heterogeneous signals into a single attention space. We observe diluted attention and higher cognitive load even on non-long videos. The bottleneck is not only what to retrieve but how to represent and fuse external knowledge with the video backbone.We present Graph-to-Frame RAG (G2F-RAG), a training free and auditable paradigm that delivers knowledge in the visual space. On the offline stage, an agent builds a problem-agnostic video knowledge graph that integrates entities, events, spatial relations, and linked world knowledge. On the online stage, a hierarchical multi-agent controller decides whether external knowledge is needed, retrieves a minimal sufficient subgraph, and renders it as a single reasoning frame appended to the video. LMMs then perform joint reasoning in a unified visual domain. This design reduces cognitive load and leaves an explicit, inspectable evidence trail.G2F-RAG is plug-and-play across backbones and scales. It yields consistent gains on diverse public benchmarks, with larger improvements in knowledge-intensive settings. Ablations further confirm that knowledge representation and delivery matter. G2F-RAG reframes retrieval as visual space knowledge fusion for robust and interpretable video reasoning.

Chengyin Hu, Weiwen Shi, Chao Li et al.

Deep neural networks (DNNs) have made remarkable strides in various computer vision tasks, including image classification, segmentation, and object detection. However, recent research has revealed a vulnerability in advanced DNNs when faced with deliberate manipulations of input data, known as adversarial attacks. Moreover, the accuracy of DNNs is heavily influenced by the distribution of the training dataset. Distortions or perturbations in the color space of input images can introduce out-of-distribution data, resulting in misclassification. In this work, we propose a brightness-variation dataset, which incorporates 24 distinct brightness levels for each image within a subset of ImageNet. This dataset enables us to simulate the effects of light and shadow on the images, so as is to investigate the impact of light and shadow on the performance of DNNs. In our study, we conduct experiments using several state-of-the-art DNN architectures on the aforementioned dataset. Through our analysis, we discover a noteworthy positive correlation between the brightness levels and the loss of accuracy in DNNs. Furthermore, we assess the effectiveness of recently proposed robust training techniques and strategies, including AugMix, Revisit, and Free Normalizer, using the ResNet50 architecture on our brightness-variation dataset. Our experimental results demonstrate that these techniques can enhance the robustness of DNNs against brightness variation, leading to improved performance when dealing with images exhibiting varying brightness levels.

Wen Yao, Xiaohu Zheng, Jun Zhang et al.

The surrogate model-based uncertainty quantification method has drawn much attention in many engineering fields. Polynomial chaos expansion (PCE) and deep learning (DL) are powerful methods for building a surrogate model. However, PCE needs to increase the expansion order to improve the accuracy of the surrogate model, which causes more labeled data to solve the expansion coefficients, and DL also requires a lot of labeled data to train the deep neural network (DNN). First of all, this paper proposes the adaptive arbitrary polynomial chaos (aPC) and proves two properties about the adaptive expansion coefficients. Based on the adaptive aPC, a semi-supervised deep adaptive arbitrary polynomial chaos expansion (Deep aPCE) method is proposed to reduce the training data cost and improve the surrogate model accuracy. For one hand, the Deep aPCE method uses two properties of the adaptive aPC to assist in training the DNN based on only a small amount of labeled data and many unlabeled data, significantly reducing the training data cost. On the other hand, the Deep aPCE method adopts the DNN to fine-tune the adaptive expansion coefficients dynamically, improving the Deep aPCE model accuracy with lower expansion order. Besides, the Deep aPCE method can directly construct accurate surrogate models of the high dimensional stochastic systems without complex dimension-reduction and model decomposition operations. Five numerical examples and an actual engineering problem are used to verify the effectiveness of the Deep aPCE method.