Action Units
PulseAugur coverage of Action Units — every cluster mentioning Action Units across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
New ActFER framework enables agentic facial expression recognition
Researchers have developed ActFER, a novel agentic framework for facial expression recognition (FER) that moves beyond passive analysis. ActFER actively acquires visual evidence by employing tools for face detection, se…
-
ARGen framework enhances dynamic facial expression recognition
Researchers have developed ARGen, a novel framework designed to improve dynamic facial expression recognition, particularly for scarce emotions. This system uses Affective Semantic Injection (ASI) to align affective kno…
-
New AI models enhance conversational speech with facial expressions and multi-person interaction
Researchers have developed new frameworks for conversational speech synthesis that incorporate facial expressions and multi-person interactions. One approach, FacialTalker, uses a large language model backbone and a vis…
-
New method enhances temporal control in text-to-motion generation
Researchers have developed a new method for text-to-motion models to improve the temporal control of individual actions, or "strokes." This approach, called Action Units (AUs), explicitly defines each stroke's timing, b…
-
New MEDN Network Decouples Motion and Emotion for Micro-Expression Recognition
Researchers have developed a new Motion-Emotion Feature Decoupling Network (MEDN) to improve micro-expression recognition. This network addresses the challenge that micro-expressions can have similar facial action units…
-
New CLIP-AUTT method enhances video emotion recognition with personalized prompts
Researchers have developed CLIP-AUTT, a novel test-time personalization method for fine-grained video emotion recognition. This approach leverages Action Units (AUs) as structured textual prompts within the CLIP vision-…