Search Results for author:
Found 21 papers, 4 papers with code
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.
Video Contrastive Learning with Global Context
Our formulation is able to capture global context in a video, thus robust to temporal content change.
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.
MoDist: Motion Distillation for Self-supervised Video Representation Learning
We present MoDist as a novel method to explicitly distill motion information into self-supervised video representations.
Unsupervised Action Segmentation with Self-supervised Feature Learning and Co-occurrence Parsing
Temporal action segmentation is a task to classify each frame in the video with an action label.
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 #3 on
Action Classification
on Kinetics-700
TubeR: Tube-Transformer for Action Detection
In this paper, we propose TubeR: the first transformer based network for end-to-end action detection, with an encoder and decoder optimized for modeling action tubes with variable lengths and aspect ratios.
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.
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.
A Comprehensive Study of Deep Video Action Recognition
Video action recognition is one of the representative tasks for video understanding.
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.
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.
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 PoseTrack2018
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.
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 #2 on
Zero-Shot Action Recognition
on HMDB51
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 #15 on
Action Recognition
on Something-Something V1
(using extra training data)
Multi-Scale Attention Network for Crowd Counting
In crowd counting datasets, people appear at different scales, depending on their distance from the camera.
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.
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.