paper-with-me

홈 › Papers

Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation

2023-03-17 · Dongsheng Wang, Xu Jia, Yang Zhang, Xinyu Zhang, Yaoyuan Wang, Ziyang Zhang, Dong Wang, Huchuan Lu

Event-based cameras are bio-inspired sensors that capture brightness change of every pixel in an asynchronous manner. Compared with frame-based sensors, event cameras have microsecond-level latency and high dynamic range, hence showing great potential for object detection under high-speed motion and poor illumination conditions. Due to sparsity and asynchronism nature with event streams, most of existing approaches resort to hand-crafted methods to convert event data into 2D grid representation. However, they are sub-optimal in aggregating information from event stream for object detection. In this work, we propose to learn an event representation optimized for event-based object detection. Specifically, event streams are divided into grids in the x-y-t coordinates for both positive and negative polarity, producing a set of pillars as 3D tensor representation. To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection. Long memory is encoded in the hidden state of adaptive convLSTMs while short memory is modeled by computing spatial-temporal correlation between event pillars at neighboring time intervals. Extensive experiments on the recently released event-based automotive detection dataset demonstrate the effectiveness of the proposed method.

📄 PDF Abstract BibTeX arXiv:2303.09919

Code (1)

wds320/AAAI_Event_based_detection 공식 구현 pytorch

Tasks

Objectobject-detectionObject Detection

Similar Papers 제목 키워드 기반

DAMe: Personalized Federated Social Event Detection with Dual Aggregation Mechanism

2024-09-01 · Xiaoyan Yu, Yifan Wei, Pu Li, Shuaishuai Zhou 외

Training social event detection models through federated learning (FedSED) aims to improve participants' performance on the task. However, existing federated learning paradigms are inadequate for achieving FedSED's objec…

Bayesian OptimizationEvent DetectionFederated LearningPersonalized Federated Learning

Rethinking Event-Based Object Detection through Representation-Level Temporal Aggregation and Model-Level Hypergraph Reasoning

2026-05-09 · Meisen Wang, Hao Deng, Wei Bao, Ma Yuanxiao 외 arxiv

Event cameras provide microsecond-level temporal resolution, low latency, and high dynamic range, offering potential for perception under fast motion and challenging illumination conditions. However, existing Event-based…

Relational ReasoningObject Detection

Generalized-Scale Object Counting with Gradual Query Aggregation

2025-11-11 · Jer Pelhan, Alan Lukezic, Matej Kristan arxiv

Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. A common approach to localize objects across multiple sizes is to merge backbone features of di…

Small Object DetectionObject Counting

MAMBA: Multi-level Aggregation via Memory Bank for Video Object Detection

2024-01-18 · Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson

State-of-the-art video object detection methods maintain a memory structure, either a sliding window or a memory queue, to enhance the current frame using attention mechanisms. However, we argue that these memory structu…

Mambaobject-detectionObject DetectionVideo Object Detection

Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation

2022-03-17 · CVPR 2022 1 · Tianfei Zhou, Meijie Zhang, Fang Zhao, Jianwu Li

Learning semantic segmentation from weakly-labeled (e.g., image tags only) data is challenging since it is hard to infer dense object regions from sparse semantic tags. Despite being broadly studied, most current efforts…

ObjectSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic Segmentation