Video Object Detection

65 papers with code • 7 benchmarks • 10 datasets

Video object detection is the task of detecting objects from a video as opposed to images.

( Image credit: Learning Motion Priors for Efficient Video Object Detection )

Libraries

Use these libraries to find Video Object Detection models and implementations

Latest papers with no code

Efficient Unsupervised Video Object Segmentation Network Based on Motion Guidance

no code yet • 10 Nov 2022

Then, the semantic features of the motion representation are obtained through the local attention mechanism in the motion guidance module to obtain the high-level semantic features of the appearance representation.

BoxMask: Revisiting Bounding Box Supervision for Video Object Detection

no code yet • 12 Oct 2022

We present a new, simple yet effective approach to uplift video object detection.

Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection

no code yet • 5 Oct 2022

Second, motivated by sequence-level semantic aggregation, we incorporate the attention-guided Semantic Proposal Feature Aggregation module to enhance object feature representation before detection.

DFA: Dynamic Feature Aggregation for Efficient Video Object Detection

no code yet • 2 Oct 2022

Video object detection is a fundamental yet challenging task in computer vision.

DAFA: Diversity-Aware Feature Aggregation for Attention-Based Video Object Detection

no code yet • IEEE Access 2022

Our method with global and local attention stages obtains 84. 5 and 85. 9 mAP on ResNet-101 and ResNeXt-101, respectively, thus achieving state-of-the-art performance without requiring additional post-processing methods.

TemporalNet: Real-time 2D-3D Video Object Detection

no code yet • Conference on Robots and Vision 2022

Our TemporalNet is a plug-and-play block that can be added to a multi-scale single-image detection network without any adjustments in the network architecture.

Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks

no code yet • 19 Aug 2022

This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection.

Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds

no code yet • 26 Jul 2022

In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i. e., the point cloud videos.

QueryProp: Object Query Propagation for High-Performance Video Object Detection

no code yet • 22 Jul 2022

The proposed QueryProp contains two propagation strategies: 1) query propagation is performed from sparse key frames to dense non-key frames to reduce the redundant computation on non-key frames; 2) query propagation is performed from previous key frames to the current key frame to improve feature representation by temporal context modeling.

Exploring Temporally Dynamic Data Augmentation for Video Recognition

no code yet • 30 Jun 2022

The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations.