Recent Audio-Visual Question Answering (AVQA) methods have advanced significantly.However, most AVQA methods lack effective mechanisms for handling missing modalities, suffering from severe performance degradation in real-world scenarios with data interruptions.Furthermore, prevailing methods for handling missing modalities predominantly rely on generative imputation to synthesize missing features.While partially effective, these methods tend to capture inter-modal commonalities but struggle to acquire unique, modalityspecific knowledge within the missing data, leading to hallucinations and compromised reasoning accuracy.To tackle these challenges, we propose R 2 ScP, a novel framework that shifts the paradigm of missing modality handling from traditional generative imputation to retrieval-based recovery.Specifically, we leverage cross-modal retrieval via unified semantic embeddings to acquire missing domain-specific knowledge.To maximize semantic restoration, we introduce a context-aware adaptive purification mechanism that eliminates latent semantic noise within the retrieved data.Additionally, we employ a two-stage training strategy to explicitly model the semantic relationships between knowledge from different sources.Extensive experiments demonstrate that R 2 ScP significantly improves AVQA and enhances robustness in modal-incomplete scenarios.1

Generating multiple appropriate facial reactions (MAFR) is essential for effective human-agent interaction. However, existing methods typically do not jointly model both local and global emotional cues, and neglect the temporal dynamics of facial expressions, leading to emotionally inconsistent and less natural reactions. In this work, we combine local and global emotional features to form a more comprehensive emotional representation. Our method further introduces motion-aware visual features that capture the dynamic evolution of facial expressions beyond static frames. By integrating both appearance and motion information within a structured generative framework, our approach enables more context-aware and temporally natural listener reactions. Experimental results demonstrate that our method outperforms existing approaches in both reaction diversity and appropriateness, which ranked first in the React 2025 challenge offline track.The implementation code can be accessed at:https://github.com/mtv-2025-react/mtv-2025-2025.git.

BACKGROUND: Protein residue-residue distance maps are used for remote homology detection, protein information estimation, and protein structure research. However, existing prediction approaches are time-consuming, and hundreds of millions of proteins are discovered each year, necessitating the development of a rapid and reliable prediction method for protein residue-residue distances. Moreover, because many proteins lack known homologous sequences, a waiting-free and alignment-free deep learning method is needed. RESULT: In this study, we propose a learning framework named FreeProtMap. In terms of protein representation processing, the proposed group pooling in FreeProtMap effectively mitigates issues arising from high-dimensional sparseness in protein representation. In terms of model structure, we have made several careful designs. Firstly, it is designed based on the locality of protein structures and triangular inequality distance constraints to improve prediction accuracy. Secondly, inference speed is improved by using additive attention and lightweight design. Besides, the generalization ability is improved by using bottlenecks and a neural network block named local microformer. As a result, FreeProtMap can predict protein residue-residue distances in tens of milliseconds and has higher precision than the best structure prediction method. CONCLUSION: Several groups of comparative experiments and ablation experiments verify the effectiveness of the designs. The results demonstrate that FreeProtMap significantly outperforms other state-of-the-art methods in accurate protein residue-residue distance prediction, which is beneficial for lots of protein research works. It is worth mentioning that we could scan all proteins discovered each year based on FreeProtMap to find structurally similar proteins in a short time because the fact that the structure similarity calculation method based on distance maps is much less time-consuming than algorithms based on 3D structures.

Research on person re-identification(Re-ID) has important value in pedestrian detection, target tracking, criminal investigation, and other related fields. In unsupervised pedestrian recognition algorithms, the accuracy of pseudo-labels is crucial to the recognition results. However, in practical scenarios, low-quality images caused by factors such as differences in camera resolution and shooting angles can affect the extraction of pedestrian features by these algorithms, thereby negatively impacting the accuracy of the labels and the learning process of the model. To address this problem, we propose an image quality enhancement algorithm for unsupervised person Re-ID (IQE). To the best of our knowledge, this study is the first to introduce detail enhancement and the application of low-light enhancement algorithms into unsupervised person Re-ID. By improving the feature extraction quality based on these two aspects, higher-quality pseudo-labels can be constructed. This method improves the accuracy of feature extraction and clustering, thereby increasing the accuracy of pseudo-labels and reducing the interference of noisy pseudo-labels. The experimental results showed that the IQE method outperformed state-of-the-art person Re-ID methods in terms of Rank-1 accuracy and mAP. Specifically, IQE achieved an 87.9% rank-1 accuracy and a 71.2% mAP on the Market-1501 dataset; a 78.1% rank-1 accuracy and a 61.7% mAP On the DukeMTMC-reID dataset; and a 51.1% rank-1 accuracy and 24.2% mAP on the MSMT17 dataset.

Person re-identification (Re-ID) arises in many applications such as video surveillance and intelligent security. Background clutter and distribution drift are two issues that cross-domain person Re-ID faces. In this research, we propose that the background clutter problem be solved by combining semantic segmentation technology with human attribute identification technology. To overcome the distribution drift problem, we propose employing MMD as a metric for distribution differences and processing methods based on feature properties. The results of the experiments reveal that our strategy yielded the best results.