Search Results for author:
Found 33 papers, 8 papers with code
Self-Supervised Multi-Object Tracking with Path Consistency
In this paper, we propose a novel concept of path consistency to learn robust object matching without using manual object identity supervision.
SkeleTR: Towrads Skeleton-based Action Recognition in the Wild
It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions, and then uses stacked Transformer encoders to capture person interactions that are important for action recognition in general scenarios.
Object-Centric Multiple Object Tracking
Unsupervised object-centric learning methods allow the partitioning of scenes into entities without additional localization information and are excellent candidates for reducing the annotation burden of multiple-object tracking (MOT) pipelines.
MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation
Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts.
SkeleTR: Towards Skeleton-based Action Recognition in the Wild
It first models the intra-person skeleton dynamics for each skeleton sequence with graph convolutions, and then uses stacked Transformer encoders to capture person interactions that are important for action recognition in the wild.
Ranked #2 on
Human Interaction Recognition
on NTU RGB+D
Large Scale Real-World Multi-Person Tracking
This paper presents a new large scale multi-person tracking dataset -- \texttt{PersonPath22}, which is over an order of magnitude larger than currently available high quality multi-object tracking datasets such as MOT17, HiEve, and MOT20 datasets.
Ranked #1 on
Multi-Object Tracking
on PersonPath22
An In-depth Study of Stochastic Backpropagation
In this paper, we provide an in-depth study of Stochastic Backpropagation (SBP) when training deep neural networks for standard image classification and object detection tasks.
Transfer of Representations to Video Label Propagation: Implementation Factors Matter
This work studies feature representations for dense label propagation in video, with a focus on recently proposed methods that learn video correspondence using self-supervised signals such as colorization or temporal cycle consistency.
Id-Free Person Similarity Learning
In this work, we explore training such a model by only using person box annotations, thus removing the necessity of manually labeling a training dataset with additional person identity annotation as these are expensive to collect.
Multi-Object Tracking with Hallucinated and Unlabeled Videos
Next, to tackle harder tracking cases, we mine hard examples across an unlabeled pool of real videos with a tracker trained on our hallucinated video data.
SiamMOT: Siamese Multi-Object Tracking
In this paper, we focus on improving online multi-object tracking (MOT).
VidTr: Video Transformer Without Convolutions
We first introduce the vanilla video transformer and show that transformer module is able to perform spatio-temporal modeling from raw pixels, but with heavy memory usage.
Ranked #15 on
Action Classification
on Charades
NUTA: Non-uniform Temporal Aggregation for Action Recognition
In the world of action recognition research, one primary focus has been on how to construct and train networks to model the spatial-temporal volume of an input video.
Directional Temporal Modeling for Action Recognition
Many current activity recognition models use 3D convolutional neural networks (e. g. I3D, I3D-NL) to generate local spatial-temporal features.
Multi-Object Tracking with Siamese Track-RCNN
Multi-object tracking systems often consist of a combination of a detector, a short term linker, a re-identification feature extractor and a solver that takes the output from these separate components and makes a final prediction.
Understanding the impact of mistakes on background regions in crowd counting
Our results show that (i) mistakes on background are substantial and they are responsible for 18-49% of the total error, (ii) models do not generalize well to different kinds of backgrounds and perform poorly on completely background images, and (iii) models make many more mistakes than those captured by the standard Mean Absolute Error (MAE) metric, as counting on background compensates considerably for misses on foreground.
Semantic Correlation Promoted Shape-Variant Context for Segmentation
In this way, the proposed network aggregates the context information of a pixel from its semantic-correlated region instead of a predefined fixed region.
Ranked #13 on
Semantic Segmentation
on COCO-Stuff test
Toward Achieving Robust Low-Level and High-Level Scene Parsing
Furthermore, we introduce a “dense skip” architecture to retain a rich set of low-level information from the pre-trained CNN, which is essential to improve the low-level parsing performance.
Multi-Scale Attention Network for Crowd Counting
In crowd counting datasets, people appear at different scales, depending on their distance from the camera.
Improving Fast Segmentation With Teacher-student Learning
Recently, segmentation neural networks have been significantly improved by demonstrating very promising accuracies on public benchmarks.
Context Contrasted Feature and Gated Multi-Scale Aggregation for Scene Segmentation
In this paper, we first propose a novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context.
Ranked #16 on
Semantic Segmentation
on COCO-Stuff test
Multimodal Recurrent Neural Networks with Information Transfer Layers for Indoor Scene Labeling
This paper proposes a new method called Multimodal RNNs for RGB-D scene semantic segmentation.
Deep Level Sets for Salient Object Detection
Our method drives the network to learn a Level Set function for salient objects so it can output more accurate boundaries and compact saliency.
Episodic CAMN: Contextual Attention-Based Memory Networks With Iterative Feedback for Scene Labeling
Scene labeling can be seen as a sequence-sequence prediction task (pixels-labels), and it is quite important to leverage relevant context to enhance the performance of pixel classification.
Improving Fully Convolution Network for Semantic Segmentation
In addition, dense skip connections are added so that the context network can be effectively optimized.
A Siamese Long Short-Term Memory Architecture for Human Re-Identification
Matching pedestrians across multiple camera views known as human re-identification (re-identification) is a challenging problem in visual surveillance.
Joint Learning of Siamese CNNs and Temporally Constrained Metrics for Tracklet Association
Then the Siamese CNN and temporally constrained metrics are jointly learned online to construct the appearance-based tracklet affinity models.
Scene Parsing with Integration of Parametric and Non-parametric Models
The local beliefs of pixels are output by CNN-Ensemble.
Recent Advances in Convolutional Neural Networks
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.
Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
In this manuscript, we integrate CNNs with HRNNs, and develop end-to-end convolutional hierarchical recurrent neural networks (C-HRNNs).
DAG-Recurrent Neural Networks For Scene Labeling
In image labeling, local representations for image units are usually generated from their surrounding image patches, thus long-range contextual information is not effectively encoded.
Ranked #18 on
Semantic Segmentation
on COCO-Stuff test
Exemplar Based Deep Discriminative and Shareable Feature Learning for Scene Image Classification
In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL).
Integrating Parametric and Non-Parametric Models For Scene Labeling
We adopt Convolutional Neural Networks (CNN) as our parametric model to learn discriminative features and classifiers for local patch classification.
