Related papers: A Scale-Invariant Trajectory Simplification Method…
Data pipelines are an essential component for end-to-end solutions that take machine learning algorithms to production. Engineering data pipelines for video-sequences poses several challenges including isolation of key-frames from video…
Progress in Multiple Object Tracking (MOT) has been historically limited by the size of the available datasets. We present an efficient framework to annotate trajectories and use it to produce a MOT dataset of unprecedented size. In our…
In this paper we propose an automatic trajectory data reconciliation to correct common errors in vision-based vehicle trajectory data. Given "raw" vehicle detection and tracking information from automatic video processing algorithms, we…
Single object tracking (SOT) heavily relies on the representation of the target object as a bounding box. However, due to the potential deformation and rotation experienced by the tracked targets, the genuine bounding box fails to capture…
Trajectory simplification is a problem encountered in areas like Robot programming by demonstration, CAD/CAM, computer vision, and in GPS-based applications like traffic analysis. This problem entails reduction of the points in a given…
We propose a semi-automatic bounding box annotation method for visual object tracking by utilizing temporal information with a tracking-by-detection approach. For detection, we use an off-the-shelf object detector which is trained…
Human annotation is always considered as ground truth in video object tracking tasks. It is used in both training and evaluation purposes. Thus, ensuring its high quality is an important task for the success of trackers and evaluations…
Conventional multi-object tracking (MOT) systems are predominantly designed for pedestrian tracking and often exhibit limited generalization to other object categories. This paper presents a generalized tracking framework capable of…
Tracking objects in soccer videos is extremely important to gather both player and team statistics, whether it is to estimate the total distance run, the ball possession or the team formation. Video processing can help automating the…
In this paper, the main task we aim to tackle is the multi-instance semi-supervised video object segmentation across a sequence of frames where only the first-frame box-level ground-truth is provided. Detection-based algorithms are widely…
Flow matching policies learn continuous velocity fields that transport noise to actions, enabling fast deterministic inference for robot manipulation. However, standard training optimizes a pointwise velocity objective while inference…
We propose a novel meta-learning framework for real-time object tracking with efficient model adaptation and channel pruning. Given an object tracker, our framework learns to fine-tune its model parameters in only a few iterations of…
Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are higher than a threshold. The objects with low detection…
The status quo approach to training object detectors requires expensive bounding box annotations. Our framework takes a markedly different direction: we transfer tracked object boxes from weakly-labeled videos to weakly-labeled images to…
Multi-object tracking (MOT) is a challenging practical problem for vision based applications. Most recent approaches for MOT use precomputed detections from models such as Faster RCNN, performing fine-tuning of bounding boxes and…
Accumulating substantial volumes of real-world driving data proves pivotal in the realm of trajectory forecasting for autonomous driving. Given the heavy reliance of current trajectory forecasting models on data-driven methodologies, we aim…
Global optimization algorithms have shown impressive performance in data-association based multi-object tracking, but handling online data remains a difficult hurdle to overcome. In this paper, we present a hybrid data association framework…
Collecting realistic driving trajectories is crucial for training machine learning models that imitate human driving behavior. Most of today's autonomous driving datasets contain only a few trajectories per location and are recorded with…
Annotating object ground truth in videos is vital for several downstream tasks in robot perception and machine learning, such as for evaluating the performance of an object tracker or training an image-based object detector. The accuracy of…
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets. However, the forced exposure to ground-truth in the training stage leads to the…