Search Results for author:
Found 11 papers, 7 papers with code
Annealed Winner-Takes-All for Motion Forecasting
Additionally, to compensate for limited performance, some approaches rely on training with a large set of hypotheses, requiring a post-selection step during inference to significantly reduce the number of predictions.
Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking
Multi-object tracking (MOT) endeavors to precisely estimate the positions and identities of multiple objects over time.
Valeo4Cast: A Modular Approach to End-to-End Forecasting
In end-to-end forecasting, the model must jointly detect and track from sensor data (cameras or LiDARs) the past trajectories of the different elements of the scene and predict their future locations.
Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression
Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations.
Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?
In fact, conventional forecasting methods are usually not trained nor tested in real-world pipelines (e. g., with upstream detection, tracking, and mapping modules).
Learning-based Spatial and Angular Information Separation for Light Field Compression
Light fields are a type of image data that capture both spatial and angular scene information by recording light rays emitted by a scene from different orientations.
DNN Training Acceleration via Exploring GPGPU Friendly Sparsity
The training phases of Deep neural network~(DNN) consumes enormous processing time and energy.
CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction
We explore the sparsity in ViT and observe that informative patches and heads are sufficient for accurate image recognition.
TransCenter: Transformers with Dense Representations for Multiple-Object Tracking
Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN).
Ranked #17 on
Multi-Object Tracking
on MOT20
(MOTA metric, using extra
training data)
How To Train Your Deep Multi-Object Tracker
In this paper, we bridge this gap by proposing a differentiable proxy of MOTA and MOTP, which we combine in a loss function suitable for end-to-end training of deep multi-object trackers.
Ranked #4 on
Multi-Object Tracking
on 2D MOT 2015
CANU-ReID: A Conditional Adversarial Network for Unsupervised person Re-IDentification
Unsupervised person re-ID is the task of identifying people on a target data set for which the ID labels are unavailable during training.
