Search Results for author:
Found 51 papers, 29 papers with code
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
Notably, our approach demonstrates a significant improvement in performance on 5 fine-grained visual recognition benchmarks, 11 few-shot image recognition datasets, and the 2 object detection datasets under the zero-shot recognition setting.
Alpha-CLIP: A CLIP Model Focusing on Wherever You Want
Alpha-CLIP not only preserves the visual recognition ability of CLIP but also enables precise control over the emphasis of image contents.
Towards Regression-Free Neural Networks for Diverse Compute Platforms
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important.
Mitigating Representation Bias in Action Recognition: Algorithms and Benchmarks
Deep learning models have achieved excellent recognition results on large-scale video benchmarks.
ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training
We present a method to train a classification system that achieves paragon performance in both error rate and NFR, at the inference cost of a single model.
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models
We propose a memory efficient method, named Stochastic Backpropagation (SBP), for training deep neural networks on videos.
MeMOT: Multi-Object Tracking with Memory
We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span.
Contrastive Neighborhood Alignment
We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model.
Long Short-Term Transformer for Online Action Detection
We present Long Short-term TRansformer (LSTR), a temporal modeling algorithm for online action detection, which employs a long- and short-term memory mechanism to model prolonged sequence data.
Ranked #3 on
Online Action Detection
on TVSeries
Semi-TCL: Semi-Supervised Track Contrastive Representation Learning
We design a new instance-to-track matching objective to learn appearance embedding that compares a candidate detection to the embedding of the tracks persisted in the tracker.
Learning Hierarchical Graph Neural Networks for Image Clustering
Our hierarchical GNN uses a novel approach to merge connected components predicted at each level of the hierarchy to form a new graph at the next level.
Harnessing Unrecognizable Faces for Improving Face Recognition
The common implementation of face recognition systems as a cascade of a detection stage and a recognition or verification stage can cause problems beyond failures of the detector.
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.
Compatibility-aware Heterogeneous Visual Search
Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery images.
Regression Bugs Are In Your Model! Measuring, Reducing and Analyzing Regressions In NLP Model Updates
Behavior of deep neural networks can be inconsistent between different versions.
TubeR: Tubelet Transformer for Video Action Detection
We propose TubeR: a simple solution for spatio-temporal video action detection.
CelebA-Spoof Challenge 2020 on Face Anti-Spoofing: Methods and Results
It is the largest face anti-spoofing dataset in terms of the numbers of the data and the subjects.
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
Learning Self-Consistency for Deepfake Detection
We propose a new method to detect deepfake images using the cue of the source feature inconsistency within the forged images.
A Comprehensive Study of Deep Video Action Recognition
Video action recognition is one of the representative tasks for video understanding.
Positive-Congruent Training: Towards Regression-Free Model Updates
Reducing inconsistencies in the behavior of different versions of an AI system can be as important in practice as reducing its overall error.
SMOT: Single-Shot Multi Object Tracking
We combine this scheme with SSD detectors by proposing a novel tracking anchor assignment module.
Online Action Detection in Streaming Videos with Time Buffers
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual frame viewed by the audience.
3D-Aided Data Augmentation for Robust Face Understanding
Data augmentation has been highly effective in narrowing the data gap and reducing the cost for human annotation, especially for tasks where ground truth labels are difficult and expensive to acquire.
Towards causal benchmarking of bias in face analysis algorithms
To address this problem we develop an experimental method for measuring algorithmic bias of face analysis algorithms, which manipulates directly the attributes of interest, e. g., gender and skin tone, in order to reveal causal links between attribute variation and performance change.
On Improving Temporal Consistency for Online Face Liveness Detection
In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system.
Ranked #4 on
Face Anti-Spoofing
on SiW (Protocol 3)
Motion Guided 3D Pose Estimation from Videos
We propose a new loss function, called motion loss, for the problem of monocular 3D Human pose estimation from 2D pose.
Ranked #19 on
3D Human Pose Estimation
on Human3.6M
Omni-sourced Webly-supervised Learning for Video Recognition
Then a joint-training strategy is proposed to deal with the domain gaps between multiple data sources and formats in webly-supervised learning.
Ranked #5 on
Action Recognition
on UCF101
(using extra training data)
Towards Backward-Compatible Representation Learning
Backward compatibility is critical to quickly deploy new embedding models that leverage ever-growing large-scale training datasets and improvements in deep learning architectures and training methods.
Convolutional Sequence Generation for Skeleton-Based Action Synthesis
It captures the temporal structure at multiple scales through the GP prior and the temporal convolutions; and establishes the spatial connection between the latent vectors and the skeleton graphs via a novel graph refining scheme.
Ranked #2 on
Human action generation
on NTU RGB+D
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)
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Trajectory Convolution for Action Recognition
How to leverage the temporal dimension is a key question in video analysis.
From Trailers to Storylines: An Efficient Way to Learn from Movies
Experiments on this dataset showed that the proposed method can substantially reduce the training time while obtaining highly effective features and coherent temporal structures.
Recognize Actions by Disentangling Components of Dynamics
Despite the remarkable progress in action recognition over the past several years, existing methods remain limited in efficiency and effectiveness.
Unsupervised Feature Learning via Non-Parametric Instance Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.
Ranked #40 on
Semi-Supervised Image Classification
on ImageNet - 1% labeled data
(Top 5 Accuracy metric)
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so.
Ranked #13 on
Contrastive Learning
on imagenet-1k
Optimizing Video Object Detection via a Scale-Time Lattice
High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e. g. those that require detecting objects from video streams in real time.
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Dynamics of human body skeletons convey significant information for human action recognition.
Face Detection through Scale-Friendly Deep Convolutional Networks
Specifically, our method achieves 76. 4 average precision on the challenging WIDER FACE dataset and 96% recall rate on the FDDB dataset with 7 frames per second (fps) for 900 * 1300 input image.
Temporal Segment Networks for Action Recognition in Videos
Furthermore, based on the temporal segment networks, we won the video classification track at the ActivityNet challenge 2016 among 24 teams, which demonstrates the effectiveness of TSN and the proposed good practices.
Ranked #5 on
Video Classification
on COIN
Temporal Action Detection with Structured Segment Networks
Detecting actions in untrimmed videos is an important yet challenging task.
Ranked #6 on
Action Recognition
on THUMOS’14
UntrimmedNets for Weakly Supervised Action Recognition and Detection
We exploit the learned models for action recognition (WSR) and detection (WSD) on the untrimmed video datasets of THUMOS14 and ActivityNet.
Ranked #3 on
Action Classification
on ActivityNet-1.2
Weakly Supervised Action Localization
Weakly-Supervised Action Recognition
A Pursuit of Temporal Accuracy in General Activity Detection
Detecting activities in untrimmed videos is an important but challenging task.
Ranked #29 on
Temporal Action Localization
on ActivityNet-1.3
Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs
Convolutional Neural Networks (CNNs) have made remarkable progress on scene recognition, partially due to these recent large-scale scene datasets, such as the Places and Places2.
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Ranked #3 on
Multimodal Activity Recognition
on EV-Action
CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016
This paper presents the method that underlies our submission to the untrimmed video classification task of ActivityNet Challenge 2016.
Towards Good Practices for Very Deep Two-Stream ConvNets
However, for action recognition in videos, the improvement of deep convolutional networks is not so evident.
Ranked #66 on
Action Recognition
on UCF101
Recognize Complex Events From Static Images by Fusing Deep Channels
A considerable portion of web images capture events that occur in our personal lives or social activities.
Zeta Hull Pursuits: Learning Nonconvex Data Hulls
Selecting a small informative subset from a given dataset, also called column sampling, has drawn much attention in machine learning.
DeepID-Net: multi-stage and deformable deep convolutional neural networks for object detection
In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty.
