SUGAR: Learning Skeleton Representation with Visual-Motion Knowledge for Action Recognition

Large Language Models (LLMs) hold rich implicit knowledge and powerful transferability. In this paper, we explore the combination of LLMs with the human skeleton to perform action classification and description. However, when treating LLM as a recognizer, two questions arise: 1) How can LLMs understand skeleton? 2) How can LLMs distinguish among actions? To address these problems, we introduce a novel paradigm named learning Skeleton representation with visUal-motion knowledGe for Action Recognition (SUGAR). In our pipeline, we first utilize off-the-shelf large-scale video models as a knowledge base to generate visual, motion information related to actions. Then, we propose to supervise skeleton learning through this prior knowledge to yield discrete representations. Finally, we use the LLM with untouched pre-training weights to understand these representations and generate the desired action targets and descriptions. Notably, we present a Temporal Query Projection (TQP) module to continuously model the skeleton signals with long sequences. Experiments on several skeleton-based action classification benchmarks demonstrate the efficacy of our SUGAR. Moreover, experiments on zero-shot scenarios show that SUGAR is more versatile than linear-based methods.

Towards Generalizable SER: Soft Labeling and Data Augmentation for Modeling Temporal Emotion Shifts in Large-Scale Multilingual Speech

Recognizing emotions in spoken communication is crucial for advanced human-machine interaction. Current emotion detection methodologies often display biases when applied cross-corpus. To address this, our study amalgamates 16 diverse datasets, resulting in 375 hours of data across languages like English, Chinese, and Japanese. We propose a soft labeling system to capture gradational emotional intensities. Using the Whisper encoder and data augmentation methods inspired by contrastive learning, our method emphasizes the temporal dynamics of emotions. Our validation on four multilingual datasets demonstrates notable zero-shot generalization. We publish our open source model weights and initial promising results after fine-tuning on Hume-Prosody.