4 papers
Towards LLM-centric Affective Visual Customization via Efficient and Precise Emotion Manipulating
Jiamin Luo, Xuqian Gu, Jingjing Wang +1
Previous studies on visual customization primarily rely on the objective alignment between various control signals (e.g., language, layout and canny) and the edited images, which l…
Omni-SILA: Towards Omni-scene Driven Visual Sentiment Identifying, Locating and Attributing in Videos
Jiamin Luo, Jingjing Wang, Junxiao Ma +3
Prior studies on Visual Sentiment Understanding (VSU) primarily rely on the explicit scene information (e.g., facial expression) to judge visual sentiments, which largely ignore im…
Sherlock: Towards Multi-scene Video Abnormal Event Extraction and Localization via a Global-local Spatial-sensitive LLM
Junxiao Ma, Jingjing Wang, Jiamin Luo +2
Prior studies on Video Anomaly Detection (VAD) mainly focus on detecting whether each video frame is abnormal or not in the video, which largely ignore the structured video semanti…
ChatASU: Evoking LLM's Reflexion to Truly Understand Aspect Sentiment in Dialogues
Yiding Liu, Jingjing Wang, Jiamin Luo +2
Aspect Sentiment Understanding (ASU) in interactive scenarios (e.g., Question-Answering and Dialogue) has attracted ever-more interest in recent years and achieved important progre…