Search Results for author:
Found 34 papers, 8 papers with code
Finding Things: Image Parsing with Regions and Per-Exemplar Detectors
This paper presents a system for image parsing, or labeling each pixel in an image with its semantic category, aimed at achieving broad coverage across hundreds of object categories, many of them sparsely sampled.
Scene Parsing with Object Instances and Occlusion Ordering
This work proposes a method to interpret a scene by assigning a semantic label at every pixel and inferring the spatial extent of individual object instances together with their occlusion relationships.
Multi-Scale Attention Network for Crowd Counting
In crowd counting datasets, people appear at different scales, depending on their distance from the camera.
Action recognition with spatial-temporal discriminative filter banks
In this work we focus on how to improve the representation capacity of the network, but rather than altering the backbone, we focus on improving the last layers of the network, where changes have low impact in terms of computational cost.
Ranked #36 on
Action Recognition
on Something-Something V1
(using extra training data)
Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications
Our training procedure builds on insights from recent video classification literature and uses a trainable 3D CNN to learn the visual features.
Ranked #4 on
Zero-Shot Action Recognition
on ActivityNet
Combining detection and tracking for human pose estimation in videos
Our approach consists of three components: (i) a Clip Tracking Network that performs body joint detection and tracking simultaneously on small video clips; (ii) a Video Tracking Pipeline that merges the fixed-length tracklets produced by the Clip Tracking Network to arbitrary length tracks; and (iii) a Spatial-Temporal Merging procedure that refines the joint locations based on spatial and temporal smoothing terms.
Ranked #1 on
Pose Tracking
on PoseTrack2017
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.
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.
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.
Exploiting weakly supervised visual patterns to learn from partial annotations
Ignoring these un-annotated labels result in loss of supervisory signal which reduces the performance of the classification models.
A Comprehensive Study of Deep Video Action Recognition
Video action recognition is one of the representative tasks for video understanding.
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.
Selective Feature Compression for Efficient Activity Recognition Inference
In this work, we focus on improving the inference efficiency of current action recognition backbones on trimmed videos, and illustrate that one action model can also cover then informative region by dropping non-informative features.
TubeR: Tubelet Transformer for Video Action Detection
We propose TubeR: a simple solution for spatio-temporal video action detection.
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
SiamMOT: Siamese Multi-Object Tracking
In this paper, we focus on improving online multi-object tracking (MOT).
SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation
However, it is quite expensive to annotate every frame in a large corpus of videos to construct a comprehensive supervised training dataset.
MaCLR: Motion-aware Contrastive Learning of Representations for Videos
We present MaCLR, a novel method to explicitly perform cross-modal self-supervised video representations learning from visual and motion modalities.
Single View Physical Distance Estimation using Human Pose
We propose a fully automated system that simultaneously estimates the camera intrinsics, the ground plane, and physical distances between people from a single RGB image or video captured by a camera viewing a 3-D scene from a fixed vantage point.
Video Contrastive Learning with Global Context
Our formulation is able to capture global context in a video, thus robust to temporal content change.
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.
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.
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.
What to look at and where: Semantic and Spatial Refined Transformer for detecting human-object interactions
We propose a novel one-stage Transformer-based semantic and spatial refined transformer (SSRT) to solve the Human-Object Interaction detection task, which requires to localize humans and objects, and predicts their interactions.
Hierarchical Self-supervised Representation Learning for Movie Understanding
Most self-supervised video representation learning approaches focus on action recognition.
SCVRL: Shuffled Contrastive Video Representation Learning
We propose SCVRL, a novel contrastive-based framework for self-supervised learning for videos.
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.
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
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
Learning for Transductive Threshold Calibration in Open-World Recognition
In deep metric learning for visual recognition, the calibration of distance thresholds is crucial for achieving desired model performance in the true positive rates (TPR) or true negative rates (TNR).
ScaleDet: A Scalable Multi-Dataset Object Detector
Our results show that ScaleDet achieves compelling strong model performance with an mAP of 50. 7 on LVIS, 58. 8 on COCO, 46. 8 on Objects365, 76. 2 on OpenImages, and 71. 8 on ODinW, surpassing state-of-the-art detectors with the same backbone.
Ranked #1 on
Object Detection
on OpenImages-v6
(using extra training data)
Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
This paper introduces innovative benchmarks to evaluate Vision-Language Models (VLMs) in real-world zero-shot recognition tasks, focusing on the granularity and specificity of prompting text.
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.
Early Action Recognition with Action Prototypes
For example, on early recognition observing only the first 10% of each video, our method improves the SOTA by +2. 23 Top-1 accuracy on Something-Something-v2, +3. 55 on UCF-101, +3. 68 on SSsub21, and +5. 03 on EPIC-Kitchens-55, where prior work used either multi-modal inputs (e. g. optical-flow) or batched inference.
