No abstract

Dynamic vision sensor (DVS) is an event-based camera capturing the changes of vision with high speed and low storage consumption. To better understand what DVS captures, we need to visualize the events. Existing methods have realized visualization. To optimize the vision experience, this paper proposes a framework to visualize events with rich information, high speed and less noise. Firstly, we propose an improved visualization approach using overlapped events based on human vision system. Secondly, we propose a video denoising method using shared dictionaries. In our experiments, the proposed method realizes the expected purpose on the whole video. CCS Concepts • Computing methodologies → Artificial intelligence → Computer vision → Computer vision problems → Reconstruction.

No abstract

Facial landmark localization is an essential component for facial recognition which is a vital technology for patients tracking in the situation of a global pandemic of COVID-19. Parameter amount and computation cost are two key factors affecting the application of facial landmark localization. In addition, the intrinsic imbalance of head pose in existing datasets has a great impact on the model generalization. To address these problems, this paper proposed a lightweight model LiteFace with multi-knowledge distillation and a pose-aware resampling strategy. Specifically, we proposed to extract multi-scale features and enhance the receptive filed of network by delicate model design to obtain an efficient architecture and improved the performance of the lightweight model by multi-knowledge distillation which combines knowledge distillation and mutual learning in a two-stage manner. To further improve the model performance and boost the generalization, we proposed a pose-aware resampling strategy that generates samples with different head poses and utilized the LaPa dataset to generate masked face images to increase data diversity. We conducted extensive ablation studies on the model design, multi-knowledge distillation and resampling strategy. The proposed method achieves 1.93% and 3.04% NME on the JD-landmark-mask val and test dataset respectively. Finally, LiteFace wins the third place in the 3rd Grand Challenge of 106-Point Facial Landmark Localization.

No abstract