YOLOV: Making Still Image Object Detectors Great at Video Object
Detection
- URL: http://arxiv.org/abs/2208.09686v1
- Date: Sat, 20 Aug 2022 14:12:06 GMT
- Title: YOLOV: Making Still Image Object Detectors Great at Video Object
Detection
- Authors: Yuheng Shi, Naiyan Wang, Xiaojie Guo
- Abstract summary: Video object detection (VID) is challenging because of the high variation of object appearance and the diverse deterioration in some frames.
This work proposes a simple yet effective strategy to address the concerns, which spends marginal overheads with significant gains in accuracy.
Our YOLOX-based model can achieve promising performance (e.g., 87.5% AP50 at over 30 FPS on the ImageNet VID dataset on a single 2080Ti GPU)
- Score: 23.039968987772543
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: Video object detection (VID) is challenging because of the high variation of
object appearance as well as the diverse deterioration in some frames. On the
positive side, the detection in a certain frame of a video, compared with in a
still image, can draw support from other frames. Hence, how to aggregate
features across different frames is pivotal to the VID problem. Most of
existing aggregation algorithms are customized for two-stage detectors. But,
the detectors in this category are usually computationally expensive due to the
two-stage nature. This work proposes a simple yet effective strategy to address
the above concerns, which spends marginal overheads with significant gains in
accuracy. Concretely, different from the traditional two-stage pipeline, we
advocate putting the region-level selection after the one-stage detection to
avoid processing massive low-quality candidates. Besides, a novel module is
constructed to evaluate the relationship between a target frame and its
reference ones, and guide the aggregation. Extensive experiments and ablation
studies are conducted to verify the efficacy of our design, and reveal its
superiority over other state-of-the-art VID approaches in both effectiveness
and efficiency. Our YOLOX-based model can achieve promising performance (e.g.,
87.5\% AP50 at over 30 FPS on the ImageNet VID dataset on a single 2080Ti GPU),
making it attractive for large-scale or real-time applications. The
implementation is simple, the demo code and models have been made available at
https://github.com/YuHengsss/YOLOV .
Related papers
- Identity-Consistent Aggregation for Video Object Detection [21.295859014601334]
In Video Object Detection (VID), a common practice is to leverage the rich temporal contexts from the video to enhance the object representations in each frame.
We propose ClipVID, a VID model equipped with Identity-Consistent Aggregation layers specifically designed for mining fine-grained and identity-consistent temporal contexts.
Experiments demonstrate the superiority of our method: a state-of-the-art (SOTA) performance (84.7% mAP) on the ImageNet VID dataset while running at a speed about 7x faster (39.3 fps) than previous SOTAs.
arXiv Detail & Related papers (2023-08-15T12:30:22Z) - DOAD: Decoupled One Stage Action Detection Network [77.14883592642782]
Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding.
Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition.
We present a decoupled one-stage network dubbed DOAD, to improve the efficiency for-temporal action detection.
arXiv Detail & Related papers (2023-04-01T08:06:43Z) - AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility [125.77396380698639]
AVisT is a benchmark for visual tracking in diverse scenarios with adverse visibility.
AVisT comprises 120 challenging sequences with 80k annotated frames, spanning 18 diverse scenarios.
We benchmark 17 popular and recent trackers on AVisT with detailed analysis of their tracking performance across attributes.
arXiv Detail & Related papers (2022-08-14T17:49:37Z) - Implicit Motion Handling for Video Camouflaged Object Detection [60.98467179649398]
We propose a new video camouflaged object detection (VCOD) framework.
It can exploit both short-term and long-term temporal consistency to detect camouflaged objects from video frames.
arXiv Detail & Related papers (2022-03-14T17:55:41Z) - Recent Trends in 2D Object Detection and Applications in Video Event
Recognition [0.76146285961466]
We discuss the pioneering works in object detection, followed by the recent breakthroughs that employ deep learning.
We highlight recent datasets for 2D object detection both in images and videos, and present a comparative performance summary of various state-of-the-art object detection techniques.
arXiv Detail & Related papers (2022-02-07T14:15:11Z) - Efficient Person Search: An Anchor-Free Approach [86.45858994806471]
Person search aims to simultaneously localize and identify a query person from realistic, uncropped images.
To achieve this goal, state-of-the-art models typically add a re-id branch upon two-stage detectors like Faster R-CNN.
In this work, we present an anchor-free approach to efficiently tackling this challenging task, by introducing the following dedicated designs.
arXiv Detail & Related papers (2021-09-01T07:01:33Z) - Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture.
We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions.
Results show our method's effectiveness in detecting small-scaled pedestrians.
arXiv Detail & Related papers (2020-08-19T13:13:01Z) - Single Shot Video Object Detector [215.06904478667337]
Single Shot Video Object Detector (SSVD) is a new architecture that novelly integrates feature aggregation into a one-stage detector for object detection in videos.
For $448 times 448$ input, SSVD achieves 79.2% mAP on ImageNet VID dataset.
arXiv Detail & Related papers (2020-07-07T15:36:26Z) - Joint Detection and Tracking in Videos with Identification Features [36.55599286568541]
We propose the first joint optimization of detection, tracking and re-identification features for videos.
Our method reaches the state-of-the-art on MOT, it ranks 1st in the UA-DETRAC'18 tracking challenge among online trackers, and 3rd overall.
arXiv Detail & Related papers (2020-05-21T21:06:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.