Image-to-image translation methods have progressed from only considering the image-level information to integrating the global- and instance-level information. However, only the foreground instances are refined, and the background semantics are taken as an entire feature, which causes a substantial loss of the semantic information in the translation. Additionally, the insufficient quality of the translated semantic regions also leads to an unsatisfactory performance of the object recognition or visual odometry tasks in which the translated images/videos are further used. In this paper, we propose a novel generative adversarial network for panoptic-level image-to-image translation (PanopticGAN). The proposed method has three advantages: (1) the extracted panoptic perception (i.e., the foreground instances and background semantic regions) as content codes are aligned with the sampled panoptic style codes, which considers the panoptic-level information to avoid the semantic information loss, and the latent space of each object has a rich fusion of content and style codes to generate the higher-fidelity results; (2) a feature masking module is proposed to extract the representations within each object contour by masks for sharpening the object boundaries; (3) the improved fidelity of the translated semantic regions further contributes to enhancing the performance of the object recognition or visual odometry tasks that the translated images/videos are used in. In this paper, we also annotate a compact panoptic segmentation dataset for the thermal-to-color translation task. Extensive experiments are conducted to demonstrate the effectiveness of our PanopticGAN over the latest methods.

Multimodal Large Language Models (MLLMs) have demonstrated remarkable multimodal emotion recognition capabilities, integrating multimodal cues from visual, acoustic, and linguistic contexts in the video to recognize human emotional states. However, existing methods have limitations. They neglect to capture the dynamics of local subtle clues in facial features and also do not leverage the contextual dependencies of the utterance-aware temporal segments in videos. These shortcomings somewhat restrict their expected effectiveness. In this work, we propose MicroEmo, a time-sensitive MLLM aimed at directing attention to the local facial clue dynamics and the contextual dependencies of utterance-aware video clips. Our model incorporates two key architectural contributions: (1) a global-local attention visual encoder that integrates global frame-level timestamp-bound image features with local facial features of temporal dynamics of subtle clues; (2) an utterance-aware video Q-Former that captures multi-scale and contextual dependencies by generating visual token sequences for each utterance segment and for the entire video then combining them. The experiments demonstrate that in a new Explainable Multimodal Emotion Recognition (EMER) task that exploits multi-modal and multi-faceted clues to predict emotions in an open-vocabulary (OV) manner, MicroEmo demonstrates its effectiveness compared with the latest methods.

Self-supervised contrastive learning has demonstrated remarkable effectiveness in learning visual representations without labeled data, yet its application to 3D local feature learning from point clouds remains underexplored. Existing methods predominantly focus on complete object shapes, neglecting the critical challenge of recognizing partial observations commonly encountered in real-world 3D perception. We propose a momentum contrastive learning framework specifically designed to learn discriminative local features from randomly sampled point cloud regions. By adapting the MoCo architecture with PointNet++ as the feature backbone, our method treats local parts of point cloud as fundamental contrastive learning units, combined with carefully designed augmentation strategies including random dropout and translation. Experiments on ShapeNet demonstrate that our approach effectively learns transferable local features and the empirical observation that approximately 30% object local part represents a practical threshold for effective learning when simulating real-world occlusion scenarios, and achieves comparable downstream classification accuracy while reducing training time by 16%.

Emotion recognition is a fundamental component of human-centered intelligent systems, supporting applications in healthcare, education, marketing, and human–computer interaction. Despite rapid progress driven by deep learning across facial, speech, textual, and multi-modal settings, the literature remains difficult to compare due to inconsistent emotion models, heterogeneous datasets, and varying evaluation protocols. This survey addresses this gap by providing a unified synthesis of deep learning-based uni-modal and multi-modal emotion recognition within a coherent analytical framework covering emotion modeling, dataset curation, representation learning, fusion strategies, and evaluation. Rather than listing methods, we organize existing work around key structural choices and trade-offs that affect generalization. For uni-modal approaches, we analyze how facial, speech, and textual methods increasingly rely on self-supervised pretraining to mitigate annotation scarcity, while retaining modality-specific limitations. For multi-modal systems, we examine alignment, modality dominance, complementarity, robustness, and the emerging role of large language models in affective reasoning. We further highlight persistent challenges, including label ambiguity, cross-dataset generalization, fairness, and the gap between benchmark performance and real-world deployment. This survey provides a unified perspective and a roadmap for future research. Resources are available at https://github.com/jackchen69/Awesome-Emotion-Models.

Despite remarkable progress in image translation, the complex scene with multiple discrepant objects remains a challenging problem. The translated images have low fidelity and tiny objects in fewer details causing unsatisfactory performance in object recognition. Without thorough object perception (i.e., bounding boxes, categories, and masks) of images as prior knowledge, the style transformation of each object will be difficult to track in translation. We propose panoptic-aware generative adversarial networks (PanopticGAN) for image-to-image translation together with a compact panoptic segmentation dataset. The panoptic perception (i.e., foreground instances and background semantics of the image scene) is extracted to achieve alignment between object content codes of the input domain and panoptic-level style codes sampled from the target style space, then refined by a proposed feature masking module for sharping object boundaries. The image-level combination between content and sampled style codes is also merged for higher fidelity image generation. Our proposed method was systematically compared with different competing methods and obtained significant improvement in both image quality and object recognition performance.