Person re-identification (Re-ID) under extremely low-light conditions suffers from severe image degradation, which significantly impairs the extraction of identity-discriminative features. Existing methods struggle to recover semantic information that is obscured under poor illumination. To better understand this problem, we conduct a comprehensive analysis of the semantic modeling behavior of Re-ID models in low-light settings. For the first time, we investigate the norm distributions of Query (Q), Key (K), and Value (V) vectors within the attention module and observe that, as illumination decreases, the norm of Query vectors in pedestrian regions drops significantly. This leads to dispersed attention and degraded feature representations. To address this issue, we propose a novel framework named Norm-Ratio Attention and Semantic Recovery Distillation Network (NRSRD), which consists of two key components: a Norm-Ratio Attention Module (NRA) and a Semantic Recovery Distillation Module (SRD). The former dynamically adjusts attention responses based on the ratio of K/Q vector norms, enhancing structural region perception while suppressing background interference. The latter transfers discriminative semantic knowledge from high-illumination auxiliary data to the low-light model, compensating for the semantic degradation caused by poor lighting. Extensive experiments on multiple publicly available low-light Re-ID benchmarks demonstrate the effectiveness and superiority of the proposed method.

Fatigue is a critical factor contributing to accidents in industries such as safety monitoring and engineering construction. Fatigue exhibits dynamic complexity and non-stationary characteristics, so there are many intermediate states of short-term variation between alert and fatigue. Capturing and learning the signs of these intermediate states is essential for accurate fatigue assessment. However, current fatigue detection methods primarily rely on coarse-grained labels, typically spanning minutes to hours, and commonly treat alert and fatigue as two distinctly separate distributions, overlooking the expression of intermediate states and oversimplifying the rich distribution information of fatigue types and levels, thereby limiting detection effectiveness. To address these, this paper explores a refined representation of fatigue in terms of three dimensions: time, type, and level, and proposes a Multi-Dimensional Fine-Grained Modeling for Fatigue Detection (MDFG). This introduces the SmallLoss to extract trustworthy samples, utilizes clustering to identify diverse subtypes under alert and fatigued states, and establishes base class sets in each state. Subsequently, a complete base class set containing intermediate state bases is constructed using the base class synthesis method, which achieves the expression of intermediate fatigue states from absence to presence. Finally, fatigue levels are quantified based on the matching between samples and the complete base class set. Moreover, to cope with the complex variability of fatigue states, MDFG employs meta-learning for training. MDFG achieves an Average accuracy improvement of 10.0% and 12.1% on two real datasets compared to methods that do not consider fine-grained information. Extensive experiments demonstrate that the MDFG exhibits superior robustness and stability among current fatigue detection methods.

With the rapid development and widespread adoption of digital media, deceptive behaviors have raised numerous ethical and security issues, making the research and advancement of deception detection technology particularly important. Most previous automated deception detection methods primarily focus on facial information in a visual context. However, from a psychological perspective, deceptive behavior extends beyond mere changes in facial expressions; it can also manifest through limb behaviors and subtle incoordination among body components. Motivated by this inconsistency, this paper attempts to model body behaviors and their relationships for deception detection. It is worth noting that some mainstream video understanding methods can roughly model head and limb information, but their holistic video input approach is easily affected by background interference. This limits their ability to focus on key body regions and subtle motion cues that reflect deception, thereby restricting detection performance. To address the above challenges, this paper proposes a Dynamic Learning Framework leveraging Body Part Relationship-Aware Modeling (DLF-BRAM). Within this framework, we segment and model the head and limb regions to reduce irrelevant background interference and enhance the accuracy of feature learning. The framework includes two main components: the Head-Limb Relationship-Aware Representation (HLRAR) module and the Dynamic Assessment Learning Strategy (DALS). The HLRAR module reveals the spatiotemporal relationship of the head, limbs, and their interactions, and learns deep feature representations for each cue, thereby highlighting the uniqueness of these cues. DALS evaluates the learning effectiveness of the three spatiotemporal relationships during training and dynamically adjusts their learning weights, preventing dominance by any single branch and promoting balanced learning. Extensive benchmark and ablation experiments demonstrate that our method outperforms most existing approaches, verifying its effectiveness.

The quality of pedestrian image retrieval is affected by the difference in illumination between images. Previous studies have used one-to-one lighting transformers to convert images taken under different lighting conditions into the target lighting. However, can we use a single lighting transformer to convert input images with various lighting conditions to the target lighting? This question motivated us to investigate the discrepancy between images generated by a Unified Lighting Transformer and the ground truth images across different illumination scales. We discovered that the modeling capability of the Unified Lighting Transformer for low-frequency information decreases gradually with an increase in the number of illuminant variations. Therefore, based on this insight, we proposed a Discriminative Feature Spectrum Consistency and Low-Frequency Information Constrained method. This method employs two constraints to enhance the Unified Lighting Transformer’s modeling capability for low-frequency information. The first mechanism enforces the constraint at the feature level by comparing the spectrum information between real and fake discriminative features. The second approach constrains the differences in pedestrian recognition features caused by the differences in low-frequency information between real and virtual images composed of low-frequency information from fake images and high-frequency information from authentic images. Our experiments show that our method outperforms other approaches and performs best across all metrics.

Video anomaly detection is a critical problem with widespread applications in domains such as security surveillance. Most existing methods focus on video anomaly detection tasks under uniform illumination conditions. However, in the real world, the situation is much more complicated. Video anomalies are widespread across periods and under different illumination conditions, which can lead to the detector model incorrectly reporting high anomaly scores. To address this challenge, we design a benchmark framework for the cross-illumination video anomaly detection task. The framework restores videos under different illumination scales to the same illumination scale. This reduces domain differences between uniformly illuminated training videos and differently illuminated test videos. Additionally, to demonstrate the illumination change problem and evaluate our model, we construct three large-scale datasets with a wide range of illumination variations. We experimentally validate our approach on three cross-illuminance video anomaly detection datasets. Experimental results show that our method outperforms existing methods regarding detection accuracy and is more robust.