no code implementations • 10 Mar 2024 • Haoxuanye Ji, Pengpeng Liang, Erkang Cheng
A 2D bounding box of an object in an image is lifted to a set of 3D anchors by associating each sampled point within the box with depth, yaw angle, and size candidates.
no code implementations • 9 Feb 2024 • Yifeng Bai, Zhirong Chen, Pengpeng Liang, Erkang Cheng
A curve cross-attention module is introduced in the Transformer decoder to calculate similarities between image features and curve queries of lanes.
1 code implementation • 18 Dec 2023 • Shihao Feng, Pengpeng Liang, Jin Gao, Erkang Cheng
Instead of performing correlation of the two branches at just one point in the network, in this paper, we present a multi-correlation Siamese Transformer network that has multiple stages and carries out feature correlation at the end of each stage based on sparse pillars.
1 code implementation • 30 Aug 2023 • Hengxu Zhang, Pengpeng Liang, Zhiyong Sun, Bo Song, Erkang Cheng
Inspired by the recent anchor free CNN-based circular object detection method (CircleNet) for ball-shape glomeruli detection in renal pathology, in this paper, we present CircleFormer, a Transformer-based circular medical object detection with dynamic anchor circles.
no code implementations • 16 Sep 2022 • Yifeng Bai, Zhirong Chen, Zhangjie Fu, Lang Peng, Pengpeng Liang, Erkang Cheng
In this paper, we propose CurveFormer, a single-stage Transformer-based method that directly calculates 3D lane parameters and can circumvent the difficult view transformation step.
Ranked #2 on 3D Lane Detection on Apollo Synthetic 3D Lane
no code implementations • 1 May 2022 • Naifan Li, Fan Song, Ying Zhang, Pengpeng Liang, Erkang Cheng
In this work, we propose a systematic study on simple Copy-Paste data augmentation for rare object detection in autonomous driving.
no code implementations • 8 Mar 2022 • Lang Peng, Zhirong Chen, Zhangjie Fu, Pengpeng Liang, Erkang Cheng
Semantic segmentation in bird's eye view (BEV) is an important task for autonomous driving.
no code implementations • 6 Jul 2021 • Chengcheng Guo, Minjie Lin, Heyang Guo, Pengpeng Liang, Erkang Cheng
To this end, we formulate vision-based localization as a data association problem that maps visual semantics to landmarks in HD map.
no code implementations • 6 May 2021 • Zhenbang Li, Yaya Shi, Jin Gao, Shaoru Wang, Bing Li, Pengpeng Liang, Weiming Hu
In this paper, we show the existence of universal perturbations that can enable the targeted attack, e. g., forcing a tracker to follow the ground-truth trajectory with specified offsets, to be video-agnostic and free from inference in a network.
no code implementations • 23 Mar 2017 • Pengpeng Liang, Yifan Wu, Hu Lu, Liming Wang, Chunyuan Liao, Haibin Ling
In this paper, we present a carefully designed planar object tracking benchmark containing 210 videos of 30 planar objects sampled in the natural environment.
no code implementations • 5 Jan 2015 • Pengpeng Liang, Chunyuan Liao, Xue Mei, Haibin Ling
Noting that the way we integrate objectness in visual tracking is generic and straightforward, we expect even more improvement by using tracker-specific objectness.