• Corpus ID: 215786559

ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking

  title={ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking},
  author={Fatemeh Sadat Saleh and Mohammad Sadegh Aliakbarian and Mathieu Salzmann and Stephen Gould},
One of the core components in online multiple object tracking (MOT) frameworks is associating new detections with existing tracklets, typically done via a scoring function. Despite the great advances in MOT, designing a reliable scoring function remains a challenge. In this paper, we introduce a probabilistic autoregressive generative model to score tracklet proposals by directly measuring the likelihood that a tracklet represents natural motion. One key property of our model is its ability to… 

Figures and Tables from this paper

Long-short Term Prediction for Occluded Multiple Object Tracking

A unified MOT framework that combines long- and short-term prediction models for online multiple object tracking, aiming at exploiting the appearance and motion of objects to handle different types of occlusions jointly is proposed.

SynDHN: Multi-Object Fish Tracker Trained on Synthetic Underwater Videos

  • M. A. MartijaP. Naval
  • Computer Science
    2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
This paper uses the Deep Hungarian Network (DHN) to repurpose DHN to become the tracking component of the algorithm by performing the task of affinity estimation between detector predictions, and considers both spatial and appearance features for affinity estimation.

Contextually Plausible and Diverse 3D Human Motion Prediction

A new variational framework that accounts for both diversity and context of the generated future motion is developed, and in contrast to existing approaches, condition the sampling of the latent variable that acts as source of diversity on the representation of the past observation, thus encouraging it to carry relevant information.

Deep Sequence Learning for Video Anticipation: From Discrete and Deterministic to Continuous and Stochastic

This research starts from anticipating a coarse representation of a deterministic future and then moves towards predicting continuous and fine-grained future representations of a stochastic process.

The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose

IKEA ASM is introduced—a three million frame, multi-view, furniture assembly video dataset that includes depth, atomic actions, object segmentation, and human poses that enables the development of holistic methods, which integrate multi-modal and multi-View data to better perform on these tasks.

MSN: Multi-Style Network for Trajectory Prediction

The Multi- Style Network is proposed, which utilizes style proposal and stylized prediction two sub-networks, to give agents multi-style pre- dictions in a novel categorical way adaptively to adaptively learn multiple diverse behavior styles through these channels.

View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums

This work proposes a hierarchical network V 2 -Net, which contains two sub-networks, to hierarchically model and predict agents’ trajectories with trajectory spectrums, and shows the competitiveness and superiority of this network on both ETH-UCY benchmark and the Stanford Drone Dataset.



Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies

The robustness of the data-driven approach is demonstrated by tracking multiple targets using their appearance, motion, and even interactions and it outperforms previous works on multiple publicly available datasets including the challenging MOT benchmark.

Multi-object Tracking with Neural Gating Using Bilinear LSTM

A novel recurrent network model, the Bilinear LSTM, is proposed in order to improve the learning of long-term appearance models via a recurrent network based on intuitions drawn from recursive least squares.

Tracking Without Bells and Whistles

Overall, Tracktor yields superior tracking performance than any current tracking method and the analysis exposes remaining and unsolved tracking challenges to inspire future research directions.

Recurrent Autoregressive Networks for Online Multi-object Tracking

This work proposes the Recurrent Autoregressive Network (RAN), a temporal generative modeling framework to characterize the appearance and motion dynamics of multiple objects over time and achieves top-ranked results on the two benchmarks.

Real-Time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identification

This paper proposes to handle unreliable detection by collecting candidates from outputs of both detection and tracking, and adopts a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of the tracker.

Multiple Hypothesis Tracking Revisited

It is demonstrated that a classical MHT implementation from the 90's can come surprisingly close to the performance of state-of-the-art methods on standard benchmark datasets, and it is shown that appearance models can be learned efficiently via a regularized least squares framework.

Online Learned Discriminative Part-Based Appearance Models for Multi-human Tracking

An online learning approach to produce discriminative part-based appearance models (DPAMs) for tracking multiple humans in real scenes by incorporating association based and category free tracking methods and shows significant improvements compared with state-of-art methods.

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking

With MOTChallenge, the work toward a novel multiple object tracking benchmark aimed to address issues of standardization, and the way toward a unified evaluation framework for a more meaningful quantification of multi-target tracking is described.

Online Multi-Object Tracking With Instance-Aware Tracker and Dynamic Model Refreshment

This paper proposes an instance-aware tracker to integrate SOT techniques for MOT by encoding awareness both within and between target models, and considers response maps from all target models and assigns spatial locations exclusively to optimize the overall accuracy.

The Way They Move: Tracking Multiple Targets with Similar Appearance

We introduce a computationally efficient algorithm for multi-object tracking by detection that addresses four main challenges: appearance similarity among targets, missing data due to targets being