Search Results for author:
Found 45 papers, 14 papers with code
Semi-supervised Learning with Weakly-Related Unlabeled Data : Towards Better Text Categorization
For empirical evaluation, we present a direct comparison with a number of state-of-the-art methods for inductive semi-supervised learning and text categorization; and we show that SSLW results in a significant improvement in categorization accuracy, equipped with a small training set and an unlabeled resource that is weakly related to the test beds."
An Integer Projected Fixed Point Method for Graph Matching and MAP Inference
When applied to MAP inference, the algorithm is a parallel extension of Iterated Conditional Modes (ICM) with climbing and convergence properties that make it a compelling alternative to the sequential ICM.
Discriminative Segment Annotation in Weakly Labeled Video
Second, we ensure that CRANE is robust to label noise, both in terms of tagged videos that fail to contain the concept as well as occasional negative videos that do.
Spatiotemporal Deformable Part Models for Action Detection
Deformable part models have achieved impressive performance for object detection, even on difficult image datasets.
Thoughts on a Recursive Classifier Graph: a Multiclass Network for Deep Object Recognition
In this manner we can learn and grow both a deep, complex graph of classifiers and a rich pool of features at different levels of abstraction and interpretation.
Recognition of Complex Events: Exploiting Temporal Dynamics between Underlying Concepts
While approaches based on bags of features excel at low-level action classification, they are ill-suited for recognizing complex events in video, where concept-based temporal representations currently dominate.
Large-Scale Video Classification with Convolutional Neural Networks
We further study the generalization performance of our best model by retraining the top layers on the UCF-101 Action Recognition dataset and observe significant performance improvements compared to the UCF-101 baseline model (63. 3% up from 43. 9%).
Ranked #9 on
Action Recognition
on Sports-1M
Features in Concert: Discriminative Feature Selection meets Unsupervised Clustering
Feature selection is an essential problem in computer vision, important for category learning and recognition.
Articulated motion discovery using pairs of trajectories
We propose an unsupervised approach for discovering characteristic motion patterns in videos of highly articulated objects performing natural, unscripted behaviors, such as tigers in the wild.
Recovering Spatiotemporal Correspondence between Deformable Objects by Exploiting Consistent Foreground Motion in Video
Given unstructured videos of deformable objects, we automatically recover spatiotemporal correspondences to map one object to another (such as animals in the wild).
Temporal Localization of Fine-Grained Actions in Videos by Domain Transfer from Web Images
To solve this problem, we propose a simple yet effective method that takes weak video labels and noisy image labels as input, and generates localized action frames as output.
Robust Video Segment Proposals With Painless Occlusion Handling
We propose a robust algorithm to generate video segment proposals.
MatchNet: Unifying Feature and Metric Learning for Patch-Based Matching
We perform a comprehensive set of experiments on standard datasets to carefully study the contributions of each aspect of MatchNet, with direct comparisons to established methods.
Coreset-Based Adaptive Tracking
We propose a method for learning from streaming visual data using a compact, constant size representation of all the data that was seen until a given moment.
Variable Rate Image Compression with Recurrent Neural Networks
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements.
Behavior Discovery and Alignment of Articulated Object Classes from Unstructured Video
On behavior discovery, we outperform the state-of-the-art Improved DTF descriptor.
Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision
Our method works both as a feature selection mechanism and as a fully competitive classifier.
The THUMOS Challenge on Action Recognition for Videos "in the Wild"
Additionally, we include a comprehensive empirical study evaluating the differences in action recognition between trimmed and untrimmed videos, and how well methods trained on trimmed videos generalize to untrimmed videos.
Discovering the Physical Parts of an Articulated Object Class From Multiple Videos
We propose a motion-based method to discover the physical parts of an articulated object class (e. g. head/torso/leg of a horse) from multiple videos.
Beyond Skip Connections: Top-Down Modulation for Object Detection
But most of these fine details are lost in the early convolutional layers.
Ranked #203 on
Object Detection
on COCO test-dev
Traffic Lights with Auction-Based Controllers: Algorithms and Real-World Data
Real-time optimization of traffic flow addresses important practical problems: reducing a driver's wasted time, improving city-wide efficiency, reducing gas emissions and improving air quality.
Cognitive Mapping and Planning for Visual Navigation
The accumulated belief of the world enables the agent to track visited regions of the environment.
Robust Adversarial Reinforcement Learning
Deep neural networks coupled with fast simulation and improved computation have led to recent successes in the field of reinforcement learning (RL).
SfM-Net: Learning of Structure and Motion from Video
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion and 3D object rotations and translations.
Motion Prediction Under Multimodality with Conditional Stochastic Networks
In this work, we present stochastic neural network architectures that handle such multimodality through stochasticity: future trajectories of objects, body joints or frames are represented as deep, non-linear transformations of random (as opposed to deterministic) variables.
WebVision Challenge: Visual Learning and Understanding With Web Data
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video clips, where actions are localized in space and time, resulting in 1. 58M action labels with multiple labels per person occurring frequently.
Ranked #6 on
Action Detection
on UCF101-24
Object category learning and retrieval with weak supervision
We consider the problem of retrieving objects from image data and learning to classify them into meaningful semantic categories with minimal supervision.
Rethinking the Faster R-CNN Architecture for Temporal Action Localization
We propose TAL-Net, an improved approach to temporal action localization in video that is inspired by the Faster R-CNN object detection framework.
Ranked #27 on
Temporal Action Localization
on THUMOS’14
Actor-Centric Relation Network
A visualization of the learned relation features confirms that our approach is able to attend to the relevant relations for each action.
Ranked #15 on
Action Recognition
on AVA v2.1
Modulated Policy Hierarchies
To achieve this, we study different modulation signals and exploration for hierarchical controllers.
D3D: Distilled 3D Networks for Video Action Recognition
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input.
Ranked #11 on
Action Recognition
on AVA v2.1
An Efficient 3D CNN for Action/Object Segmentation in Video
Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years.
Ranked #64 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
Selfie Drone Stick: A Natural Interface for Quadcopter Photography
This paper describes two key innovations required to deploy deep reinforcement learning models on a real robot: 1) an abstract state representation for transferring learning from simulation to the hardware platform, and 2) reward shaping and staging paradigms for training the controller.
Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows
Monocular 3D human pose and shape estimation is challenging due to the many degrees of freedom of the human body and thedifficulty to acquire training data for large-scale supervised learning in complex visual scenes.
Ranked #54 on
3D Human Pose Estimation
on 3DPW
(PA-MPJPE metric)
Speech2Action: Cross-modal Supervision for Action Recognition
We train a BERT-based Speech2Action classifier on over a thousand movie screenplays, to predict action labels from transcribed speech segments.
Learning Video Representations from Textual Web Supervision
Based on this observation, we propose to use text as a method for learning video representations.
The End-of-End-to-End: A Video Understanding Pentathlon Challenge (2020)
This report summarizes the results of the first edition of the challenge together with the findings of the participants.
Neural Descent for Visual 3D Human Pose and Shape
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image.
Ranked #62 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
The unsupervised learning process is repeated over several generations, in which each edge becomes a "student" and also part of different ensemble "teachers" for training other students.
THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers
We present THUNDR, a transformer-based deep neural network methodology to reconstruct the 3d pose and shape of people, given monocular RGB images.
Ranked #41 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
Discrete Representations Strengthen Vision Transformer Robustness
Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition.
Ranked #3 on
Domain Generalization
on Stylized-ImageNet
HSPACE: Synthetic Parametric Humans Animated in Complex Environments
We combine a hundred diverse individuals of varying ages, gender, proportions, and ethnicity, with hundreds of motions and scenes, as well as parametric variations in body shape (for a total of 1, 600 different humans), in order to generate an initial dataset of over 1 million frames.
Ranked #1 on
3D Human Pose Estimation
on HSPACE
Self-supervised Hypergraphs for Learning Multiple World Interpretations
Thus, each node could be an input node in some hyperedges and an output node in others.
