Publications (6)
Multi-Target Tracking with Dependent Likelihood Structures in Labeled Random Finite Set Filters
Lingji Chen
In multi-target tracking, a data association hypothesis assigns measurements to tracks, and the hypothesis likelihood (of the joint target-measurement associations) is used to comp…
MotionTrack: End-to-End Transformer-based Multi-Object Tracing with LiDAR-Camera Fusion
Ce Zhang, Chengjie Zhang, Yiluan Guo +2
Multiple Object Tracking (MOT) is crucial to autonomous vehicle perception. End-to-end transformer-based algorithms, which detect and track objects simultaneously, show great poten…
A Merge/Split Algorithm for Multitarget Tracking Using Generalized Labeled Multi-Bernoulli Filters
Lingji Chen
The class of Labeled Random Finite Set filters known as the delta-Generalized Labeled Multi-Bernoulli (dGLMB) filter represents the filtering density as a set of weighted hypothese…
Roos' Matrix Permanent Approximation Bounds for Data Association Probabilities
Lingji Chen
Matrix permanent plays a key role in data association probability calculations. Exact algorithms (such as Ryser's) scale exponentially with matrix size. Fully polynomial time rando…
How to Backpropagate through Hungarian in Your DETR?
Lingji Chen, Alok Sharma, Chinmay Shirore +2
The DEtection TRansformer (DETR) approach, which uses a transformer encoder-decoder architecture and a set-based global loss, has become a building block in many transformer based…
Detection Is Tracking: Point Cloud Multi-Sweep Deep Learning Models Revisited
Lingji Chen
Conventional tracking paradigm takes in instantaneous measurements such as range and bearing, and produces object tracks across time. In applications such as autonomous driving, li…