Event Trajectory Estimation via Robust Model Fitting for Efficient Event-based Object Tracking
The proposed EDA approach effectively and explicitly handles the event data association and fusion problem by performing robust multi-structural model fitting on event data to estimate accurate event trajectories.
Detecting Every Object in Events: A Robust and Efficient Approach for Class-Agnostic Open-World Object Detection
The proposed Detecting Every Object in Events (DEOE) approach leverages the unique characteristics of event cameras, such as sub-millisecond latency and high dynamic range, to achieve robust and efficient class-agnostic open-world object detection. DEOE utilizes spatio-temporal consistency and task disentanglement to identify and incorporate potential unknown objects during training, enhancing the model's generalization capabilities.
Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction
This paper proposes a unified evaluation methodology and an open-source framework called EVREAL to comprehensively benchmark and analyze various event-based video reconstruction methods from the literature.
Efficient and Adaptive Scene-Aware Sparse Transformer for High-Performance Event-based Object Detection
The proposed Scene Adaptive Sparse Transformer (SAST) achieves a remarkable balance between performance and efficiency for event-based object detection by enabling window-token co-sparsification and scene-specific sparsity optimization.
Hypergraph-based Multi-View Action Recognition using Event Cameras: A Comprehensive Framework for Leveraging Complementary Information from Multiple Viewpoints
The core message of this paper is to introduce a hypergraph-based framework called HyperMV that effectively fuses features from different viewpoints and temporal segments to address the challenges of information deficit and semantic misalignment in multi-view event-based action recognition.
© 2024 by Linnk AI