Search Results for author:
Found 12 papers, 3 papers with code
UniMODE: Unified Monocular 3D Object Detection
To address these challenges, we build a detector based on the bird's-eye-view (BEV) detection paradigm, where the explicit feature projection is beneficial to addressing the geometry learning ambiguity when employing multiple scenarios of data to train detectors.
GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping
Besides, GroupLane with ResNet18 still surpasses PersFormer by 4. 9% F1 score, while the inference speed is nearly 7x faster and the FLOPs is only 13. 3% of it.
The 1st-place Solution for CVPR 2023 OpenLane Topology in Autonomous Driving Challenge
We present the 1st-place solution of OpenLane Topology in Autonomous Driving Challenge.
MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking
Although end-to-end multi-object trackers like MOTR enjoy the merits of simplicity, they suffer from the conflict between detection and association seriously, resulting in unsatisfactory convergence dynamics.
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks.
Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation
VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes.
Delving into the Pre-training Paradigm of Monocular 3D Object Detection
(2) Combining depth estimation and 2D object detection is a promising M3OD pre-training baseline.
Diversity Matters: Fully Exploiting Depth Clues for Reliable Monocular 3D Object Detection
To tackle this problem, we propose a depth solving system that fully explores the visual clues from the subtasks in M3OD and generates multiple estimations for the depth of each target.
Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking
To this end, we propose a strategy, namely multi-view trajectory contrastive learning, in which each trajectory is represented as a center vector.
Dynamic Graph Learning-Neural Network for Multivariate Time Series Modeling
The model acquires static and dynamic graph matrices from data to model long- and short-term patterns respectively.
RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representation
Existing online multiple object tracking (MOT) algorithms often consist of two subtasks, detection and re-identification (ReID).
Enabling the Network to Surf the Internet
Few-shot learning is challenging due to the limited data and labels.
