Search Results for author:
Found 31 papers, 13 papers with code
Generic Tubelet Proposals for Action Localization
Our class-independent TPN outperforms other tubelet generation methods, and our unified temporal deep network achieves state-of-the-art localization results on all three datasets.
Probabilistic Video Generation using Holistic Attribute Control
Videos express highly structured spatio-temporal patterns of visual data.
SECaps: A Sequence Enhanced Capsule Model for Charge Prediction
In this paper, we propose a Sequence Enhanced Capsule model, dubbed as SECaps model, to relieve this problem.
A Variational Auto-Encoder Model for Stochastic Point Processes
We propose a novel probabilistic generative model for action sequences.
Variational Autoencoders with Jointly Optimized Latent Dependency Structure
In particular, we express the latent variable space of a variational autoencoder (VAE) in terms of a Bayesian network with a learned, flexible dependency structure.
Generative Model with Dynamic Linear Flow
However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive models.
Lifelong GAN: Continual Learning for Conditional Image Generation
This makes it possible to perform image-conditioned generation tasks in a lifelong learning setting.
LayoutVAE: Stochastic Scene Layout Generation From a Label Set
Recently there is an increasing interest in scene generation within the research community.
Learning from Partially-Observed Multimodal Data with Variational Autoencoders
Learning from only partially-observed data for imputation has been an active research area.
Arbitrarily-conditioned Data Imputation
In this paper, we propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows.
Variational Selective Autoencoder
Despite promising progress on unimodal data imputation (e. g. image inpainting), models for multimodal data imputation are far from satisfactory.
Point Process Flows
Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature.
AirRL: A Reinforcement Learning Approach to Urban Air Quality Inference
The model consists of two modules: a station selector and an air quality regressor.
Improving Sequential Latent Variable Models with Autoregressive Flows
We propose an approach for improving sequence modeling based on autoregressive normalizing flows.
Jacobian Determinant of Normalizing Flows
In this paper, we show that the Jacobian determinant mapping is unique for the given distributions, hence the likelihood objective of flows has a unique global optimum.
Variational Selective Autoencoder: Learning from Partially-Observed Heterogeneous Data
Learning from heterogeneous data poses challenges such as combining data from various sources and of different types.
Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Tracking
Then the association problem turns into a general graph matching between tracklet graph and detection graph.
Piggyback GAN: Efficient Lifelong Learning for Image Conditioned Generation
In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.
Agent Forecasting at Flexible Horizons using ODE Flows
In this work we describe OMEN, a neural ODE based normalizing flow for the prediction of marginal distributions at flexible evaluation horizons, and apply it to agent position forecasting.
DeepFusionMOT: A 3D Multi-Object Tracking Framework Based on Camera-LiDAR Fusion with Deep Association
This association mechanism realizes tracking of an object in a 2D domain when the object is far away and only detected by the camera, and updating of the 2D trajectory with 3D information obtained when the object appears in the LiDAR field of view to achieve a smooth fusion of 2D and 3D trajectories.
Ranked #1 on
Multi-Object Tracking
on KITTI Tracking test
Densely Constrained Depth Estimator for Monocular 3D Object Detection
So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation.
3D Multi-Object Tracking Based on Uncertainty-Guided Data Association
In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage.
3D Video Object Detection with Learnable Object-Centric Global Optimization
We explore long-term temporal visual correspondence-based optimization for 3D video object detection in this work.
Learnable Graph Matching: A Practical Paradigm for Data Association
Data association is at the core of many computer vision tasks, e. g., multiple object tracking, image matching, and point cloud registration.
You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance.
Weakly Supervised 3D Object Detection with Multi-Stage Generalization
We devise the DoubleClustering algorithm to obtain object clusters from reconstructed scene-level points, and further enhance the model's detection capabilities by developing three stages of generalization: progressing from complete to partial, static to dynamic, and close to distant.
Tracking Objects with 3D Representation from Videos
In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space.
Localization-Guided Track: A Deep Association Multi-Object Tracking Framework Based on Localization Confidence of Detections
However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified.
AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
Following this, the chosen articles are subjected to zero-shot summarization to attain succinct context.
Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
In autonomous driving, predicting future events in advance and evaluating the foreseeable risks empowers autonomous vehicles to better plan their actions, enhancing safety and efficiency on the road.
Rethinking Test-time Likelihood: The Likelihood Path Principle and Its Application to OOD Detection
Second, introducing new theoretic tools such as nearly essential support, essential distance and co-Lipschitzness, we obtain non-asymptotic provable OOD detection guarantees for certain distillation of the minimal sufficient statistics.
