Related papers: End-to-end Recurrent Multi-Object Tracking and Tra…
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects. Most current approaches for…
Reasoning about objects, relations, and physics is central to human intelligence, and a key goal of artificial intelligence. Here we introduce the interaction network, a model which can reason about how objects in complex systems interact,…
Online multi-object tracking (MOT) is extremely important for high-level spatial reasoning and path planning for autonomous and highly-automated vehicles. In this paper, we present a modular framework for tracking multiple objects…
The rapid advancement of the automotive industry towards automated and semi-automated vehicles has rendered traditional methods of vehicle interaction, such as touch-based and voice command systems, inadequate for a widening range of…
Autonomous robots operating in open and changing environments cannot always rely on predefined inputs, outputs, and action routines. Although existing learning methods enable robots to improve their performance through environmental…
Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a wide variety of physical objects that differ greatly in terms…
Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-oriented memory into a multi-object manipulation reasoning and…
The ability to detect and track objects in the visual world is a crucial skill for any intelligent agent, as it is a necessary precursor to any object-level reasoning process. Moreover, it is important that agents learn to track objects…
Recent unsupervised multi-object detection models have shown impressive performance improvements, largely attributed to novel architectural inductive biases. Unfortunately, they may produce suboptimal object encodings for downstream tasks.…
Referring understanding is a fundamental task that bridges natural language and visual content by localizing objects described in free-form expressions. However, existing works are constrained by limited language expressiveness, lacking the…
3D multi-object tracking (MOT) and trajectory forecasting are two critical components in modern 3D perception systems. We hypothesize that it is beneficial to unify both tasks under one framework to learn a shared feature representation of…
The ability to recognize, localize and track dynamic objects in a scene is fundamental to many real-world applications, such as self-driving and robotic systems. Yet, traditional multiple object tracking (MOT) benchmarks rely only on a few…
Multi-object tracking (MOT) is the task of estimating the state trajectories of an unknown and time-varying number of objects over a certain time window. Several algorithms have been proposed to tackle the multi-object smoothing task, where…
A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association. This pipeline is partially motivated by recent progress in both object…
The interactions between human and objects are important for recognizing object-centric actions. Existing methods usually adopt a two-stage pipeline, where object proposals are first detected using a pretrained detector, and then are fed to…
This paper presents to the best of our knowledge the first end-to-end object tracking approach which directly maps from raw sensor input to object tracks in sensor space without requiring any feature engineering or system identification in…
In current perception systems applied to the rebuilding of the environment for intelligent vehicles, the part reserved to object association for the tracking is increasingly significant. This allows firstly to follow the objects temporal…
Imagine experiencing a crash as the passenger of an autonomous vehicle. Wouldn't you want to know why it happened? Current end-to-end optimizable deep neural networks (DNNs) in 3D detection, multi-object tracking, and motion forecasting…
Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e,…
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce…