Longlong Jing

Longlong Jing

Auto-generated profile, based on publicly available information

Longlong Jing

The Graduate Center, City University of New York, New York, NY 10016, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 May 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LJLonglong Jing
Longlong Jing
YTYingli Tian
Yingli Tian
Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods from images or videos. First, the motivation, general pipeline, and terminologies of this field are described. Then the common deep neural network architectures that used for self-supervised learning are summarized. Next, the schema and evaluation metrics of self-supervised learning methods are reviewed followed by the commonly used datasets for images, videos, audios, and 3D data, as well as the existing self-supervised visual feature learning methods. Finally, quantitative performance comparisons of the reviewed methods on benchmark datasets are summarized and discussed for both image and video feature learning. At last, this paper is concluded and lists a set of promising future directions for self-supervised visual feature learning.

16 November 2020 in Computerized Medical Imaging and Graphics
Verified
Journal Article
Closed access
JTJiaxing Tan
Jiaxing Tan
LJLonglong Jing
Longlong Jing
YHYumei Huo
Yumei Huo
Lihong LiLihong Li
Lihong Li
OAOguz Akin
Oguz Akin
YTYingli Tian
Yingli Tian

20 December 2023 in International Journal of Artificial Intelligence and Robotics Research
Verified
Journal Article
Closed access
EVElahe Vahdani
Elahe Vahdani
LJLonglong Jing
Longlong Jing
MHMatt Huenerfauth
Matt Huenerfauth
YTYingli Tian
Yingli Tian

8 June 2022 in arXiv
Verified
Preprint
Open access
PDF file
LJLonglong Jing
Longlong Jing
RYRuichi Yu
Ruichi Yu
HKHenrik Kretzschmar
Henrik Kretzschmar
KLKang Li
Kang Li
CQCharles R. Qi
Charles R. Qi
DADragomir Anguelov
Dragomir Anguelov
Monocular image-based 3D perception has become an active research area in recent years owing to its applications in autonomous driving. Approaches to monocular 3D perception including detection and tracking, however, often yield inferior performance when compared to LiDAR-based techniques. Through systematic analysis, we identified that per-object depth estimation accuracy is a major factor bounding the performance. Motivated by this observation, we propose a multi-level fusion method that combines different representations (RGB and pseudo-LiDAR) and temporal information across multiple frames for objects (tracklets) to enhance per-object depth estimation. Our proposed fusion method achieves the state-of-the-art performance of per-object depth estimation on the Waymo Open Dataset, the KITTI detection dataset, and the KITTI MOT dataset. We further demonstrate that by simply replacing estimated depth with fusion-enhanced depth, we can achieve significant improvements in monocular 3D perception tasks, including detection and tracking.

23 July 2022 in arXiv
Verified
Preprint
Open access
PDF file
ZFZiyue Feng
Ziyue Feng
LYLiang Yang
Liang Yang
LJLonglong Jing
Longlong Jing
HWHAIYAN WANG
HAIYAN WANG
YTYingli Tian
Yingli Tian
BLBing Li
Bing Li
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the mismatch and occlusion problems introduced by object motions. Existing dynamic-object-focused methods only partially solved the mismatch problem at the training loss level. In this paper, we accordingly propose a novel multi-frame monocular depth prediction method to solve these problems at both the prediction and supervision loss levels. Our method, called DynamicDepth, is a new framework trained via a self-supervised cycle consistent learning scheme. A Dynamic Object Motion Disentanglement (DOMD) module is proposed to disentangle object motions to solve the mismatch problem. Moreover, novel occlusion-aware Cost Volume and Re-projection Loss are designed to alleviate the occlusion effects of object motions. Extensive analyses and experiments on the Cityscapes and KITTI datasets show that our method significantly outperforms the state-of-the-art monocular depth prediction methods, especially in the areas of dynamic objects. Code is available at https://github.com/AutoAILab/DynamicDepth