Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning

Reinforcement learning in large reasoning models enables learning from feedback on their outputs, making it particularly valuable in scenarios where fine-tuning data is limited. However, its application in multi-modal human activity recognition (HAR) domains remains largely underexplored. Our work extends reinforcement learning to the human activity recognition domain with multimodal large language models. By incorporating visual reinforcement learning in the training process, the model's generalization ability on few-shot recognition can be greatly improved. Additionally, visual reinforcement learning can enhance the model's reasoning ability and enable explainable analysis in the inference stage. We name our few-shot human activity recognition method with visual reinforcement learning FAVOR. Specifically, our approach first utilizes a multimodal large language model (MLLM) to generate multiple candidate responses for the human activity image, each containing reasoning traces and final answers. These responses are then evaluated using reward functions, and the MLLM model is subsequently optimized using the Group Relative Policy Optimization (GRPO) algorithm. In this way, the MLLM model can be adapted to human activity recognition with only a few samples. Extensive experiments on four human activity recognition datasets and five different settings demonstrate the superiority of the proposed method.

C-AAE: Compressively Anonymizing Autoencoders for Privacy-Preserving Activity Recognition in Healthcare Sensor Streams

Wearable accelerometers and gyroscopes encode fine-grained behavioural signatures that can be exploited to re-identify users, making privacy protection essential for healthcare applications. We introduce C-AAE, a compressive anonymizing autoencoder that marries an Anonymizing AutoEncoder (AAE) with Adaptive Differential Pulse-Code Modulation (ADPCM). The AAE first projects raw sensor windows into a latent space that retains activity-relevant features while suppressing identity cues. ADPCM then differentially encodes this latent stream, further masking residual identity information and shrinking the bitrate. Experiments on the MotionSense and PAMAP2 datasets show that C-AAE cuts user re-identification F1 scores by 10-15 percentage points relative to AAE alone, while keeping activity-recognition F1 within 5 percentage points of the unprotected baseline. ADPCM also reduces data volume by roughly 75 %, easing transmission and storage overheads. These results demonstrate that C-AAE offers a practical route to balancing privacy and utility in continuous, sensor-based activity recognition for healthcare.