{"total":20,"rows":[{"id":"2507.15765","title":"Learning from Heterogeneity: Generalizing Dynamic Facial Expression Recognition via Distributionally Robust Optimization","created":"2025-07-21","cited_by_count":19,"area":null},{"id":"2408.16272","title":"Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Grounding","created":"2024-08-29","cited_by_count":10,"area":null},{"id":"2503.15417","title":"Temporal Regularization Makes Your Video Generator Stronger","created":"2025-03-19","cited_by_count":10,"area":null},{"id":"2505.13437","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2510.06231","title":"CML-Bench: A Framework for Evaluating and Enhancing LLM-Powered Movie Scripts Generation","created":"2025-10-01","cited_by_count":7,"area":null},{"id":"2408.13123","title":"Evidential Deep Partial Multi-View Classification With Discount Fusion","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2505.02331","title":"VAEmo: Efficient Representation Learning for Visual-Audio Emotion with Knowledge Injection","created":"2025-05-05","cited_by_count":5,"area":null},{"id":"2408.08645","title":"PolyFootNet: Extracting Polygonal Building Footprints in Off-Nadir Remote Sensing Images","created":"2024-08-16","cited_by_count":3,"area":null},{"id":"2412.02114","title":"Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning","created":"2024-12-03","cited_by_count":2,"area":null},{"id":"2601.13225","title":"Not all Blends are Equal: The BLEMORE Dataset of Blended Emotion Expressions with Relative Salience Annotations","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2603.27999","title":"CLIP-AUTT: Test-Time Personalization with Action Unit Prompting for Fine-Grained Video Emotion Recognition","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2409.06270","title":"Towards Robust Uncertainty-Aware Incomplete Multi-View Classification","created":"2024-09-10","cited_by_count":1,"area":null},{"id":"2506.00903","title":"Leveraging CLIP Encoder for Multimodal Emotion Recognition","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.20867","title":"Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation","created":"2025-06-25","cited_by_count":1,"area":null},{"id":"2507.11892","title":"From Coarse to Nuanced: Cross-Modal Alignment of Fine-Grained Linguistic Cues and Visual Salient Regions for Dynamic Emotion Recognition","created":"2025-07-16","cited_by_count":0,"area":null},{"id":"2511.21021","title":"Structure-Aware Prototype Guided Trusted Multi-View Classification","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2604.02397","title":"Variational Encoder--Multi-Decoder (VE-MD) for Privacy-by-functional-design (Group) Emotion Recognition","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.10541","title":"Bidirectional Learning of Facial Action Units and Expressions via Structured Semantic Mapping across Heterogeneous Datasets","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2606.26942","title":"TraMP-LLaMA: Generative Interpretability with Decoupled Instruction Tuning for Facial Expression Quality Assessment","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2609.17130","title":"Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition","created":"2026-09-15","cited_by_count":0,"area":null}],"next_cursor":null}