Search Results for author:
Found 111 papers, 49 papers with code
Topical Video Object Discovery from Key Frames by Modeling Word Co-occurrence Prior
We show that such data driven co-occurrence information from bottom-up can conveniently be incorporated in LDA with a Gaussian Markov prior, which combines top down probabilistic topic modeling with bottom up priors in a unified model.
Probabilistic Elastic Matching for Pose Variant Face Verification
By augmenting each feature with its location, a Gaussian mixture model (GMM) is trained to capture the spatialappearance distribution of all face images in the training corpus.
Hash-SVM: Scalable Kernel Machines for Large-Scale Visual Classification
This paper presents a novel algorithm which uses compact hash bits to greatly improve the efficiency of non-linear kernel SVM in very large scale visual classification problems.
Semi-supervised Relational Topic Model for Weakly Annotated Image Recognition in Social Media
In such way, we can efficiently leverage the loosely related tags, and build an intermediate level representation for a collection of weakly annotated images.
Unsupervised One-Class Learning for Automatic Outlier Removal
Outliers are pervasive in many computer vision and pattern recognition problems.
Efficient Boosted Exemplar-based Face Detection
Despite the fact that face detection has been studied intensively over the past several decades, the problem is still not completely solved.
Hierarchical-PEP Model for Real-World Face Recognition
We apply the PEP model hierarchically to decompose a face image into face parts at different levels of details to build pose-invariant part-based face representations.
Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification
We follow the learning-to-rank methodology and learn a similarity function to maximize the difference between the similarity scores of matched and unmatched images for a same person.
A Convolutional Neural Network Cascade for Face Detection
To improve localization effectiveness, and reduce the number of candidates at later stages, we introduce a CNN-based calibration stage after each of the detection stages in the cascade.
Multi-Class Multi-Annotator Active Learning With Robust Gaussian Process for Visual Recognition
Based on the EP approximation inference, a generalized Expectation Maximization (GEM) algorithm is derived to estimate both the parameters for instances and the quality of each individual annotator.
Learning Discriminative Reconstructions for Unsupervised Outlier Removal
We study the problem of automatically removing outliers from noisy data, with application for removing outlier images from an image collection.
Neural Aggregation Network for Video Face Recognition
The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition.
Ranked #7 on
Face Verification
on IJB-A
Counting Grid Aggregation for Event Retrieval and Recognition
Event retrieval and recognition in a large corpus of videos necessitates a holistic fixed-size visual representation at the video clip level that is comprehensive, compact, and yet discriminative.
Ordinal Regression With Multiple Output CNN for Age Estimation
To address the non-stationary property of aging patterns, age estimation can be cast as an ordinal regression problem.
A Multi-Level Contextual Model For Person Recognition in Photo Albums
Our new framework enables efficient use of these complementary multi-level contextual cues to improve overall recognition rates on the photo album person recognition task, as demonstrated through state-of-the-art results on a challenging public dataset.
Supervised Transformer Network for Efficient Face Detection
For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector.
Ranked #5 on
Face Detection
on PASCAL Face
Revisiting Deep Intrinsic Image Decompositions
While invaluable for many computer vision applications, decomposing a natural image into intrinsic reflectance and shading layers represents a challenging, underdetermined inverse problem.
Collaborative Deep Reinforcement Learning for Joint Object Search
We examine the problem of joint top-down active search of multiple objects under interaction, e. g., person riding a bicycle, cups held by the table, etc..
StyleBank: An Explicit Representation for Neural Image Style Transfer
It also enables us to conduct incremental learning to add a new image style by learning a new filter bank while holding the auto-encoder fixed.
Coherent Online Video Style Transfer
Training a feed-forward network for fast neural style transfer of images is proven to be successful.
CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
Our approach models an image as a composition of label and latent attributes in a probabilistic model.
Visual Attribute Transfer through Deep Image Analogy
We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure.
Hidden Talents of the Variational Autoencoder
Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying distribution.
ER3: A Unified Framework for Event Retrieval, Recognition and Recounting
We develop a unified framework for complex event retrieval, recognition and recounting.
Correlational Gaussian Processes for Cross-Domain Visual Recognition
A set of correlational tensors is adopted to model the relationship within a single domain as well as across multiple domains.
Order-Preserving Wasserstein Distance for Sequence Matching
We present a new distance measure between sequences that can tackle local temporal distortion and periodic sequences with arbitrary starting points.
A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing
This paper proposes a deep neural network structure that exploits edge information in addressing representative low-level vision tasks such as layer separation and image filtering.
Fast, Accurate Thin-Structure Obstacle Detection for Autonomous Mobile Robots
This work is devoted to a task that is indispensable for safety yet was largely overlooked in the past -- detecting obstacles that are of very thin structures, such as wires, cables and tree branches.
Hierarchical Multimodal LSTM for Dense Visual-Semantic Embedding
We address the problem of dense visual-semantic embedding that maps not only full sentences and whole images but also phrases within sentences and salient regions within images into a multimodal embedding space.
Understanding and Predicting The Attractiveness of Human Action Shot
Selecting attractive photos from a human action shot sequence is quite challenging, because of the subjective nature of the "attractiveness", which is mainly a combined factor of human pose in action and the background.
Semi-supervised FusedGAN for Conditional Image Generation
We achieve this by fusing two generators: one for unconditional image generation, and the other for conditional image generation, where the two partly share a common latent space thereby disentangling the generation.
Stereoscopic Neural Style Transfer
This paper presents the first attempt at stereoscopic neural style transfer, which responds to the emerging demand for 3D movies or AR/VR.
Attention-based Temporal Weighted Convolutional Neural Network for Action Recognition
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs).
Stacked Cross Attention for Image-Text Matching
Prior work either simply aggregates the similarity of all possible pairs of regions and words without attending differentially to more and less important words or regions, or uses a multi-step attentional process to capture limited number of semantic alignments which is less interpretable.
Ranked #4 on
Image Retrieval
on PhotoChat
Towards Open-Set Identity Preserving Face Synthesis
We then recombine the identity vector and the attribute vector to synthesize a new face of the subject with the extracted attribute.
Decouple Learning for Parameterized Image Operators
Many different deep networks have been used to approximate, accelerate or improve traditional image operators, such as image smoothing, super-resolution and denoising.
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks
Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model.
Reinforced Pipeline Optimization: Behaving Optimally with Non-Differentiabilities
Many machine learning systems are implemented as pipelines.
Conscious Inference for Object Detection
Current Convolutional Neural Network (CNN)-based object detection models adopt strictly feedforward inference to predict the final detection results.
Gated Context Aggregation Network for Image Dehazing and Deraining
Image dehazing aims to recover the uncorrupted content from a hazy image.
Ranked #1 on
Rain Removal
on DID-MDN
A Compositional Textual Model for Recognition of Imperfect Word Images
Printed text recognition is an important problem for industrial OCR systems.
Optical Character Recognition (OCR)
Printed Text Recognition
A General Decoupled Learning Framework for Parameterized Image Operators
To overcome this limitation, we propose a new decoupled learning algorithm to learn from the operator parameters to dynamically adjust the weights of a deep network for image operators, denoted as the base network.
Any-Precision Deep Neural Networks
When all layers are set to low-bits, we show that the model achieved accuracy comparable to dedicated models trained at the same precision.
Ladder Loss for Coherent Visual-Semantic Embedding
For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way -- relevant or irrelevant, and all "irrelevant" candidates are uniformly pushed away from the query by an equal margin in the embedding space, regardless of their various proximity to the query.
Calibrated Domain-Invariant Learning for Highly Generalizable Large Scale Re-Identification
Many real-world applications, such as city-scale traffic monitoring and control, requires large-scale re-identification.
Adversarial Ranking Attack and Defense
In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.
SaccadeNet: A Fast and Accurate Object Detector
Object detection is an essential step towards holistic scene understanding.
Ranked #194 on
Object Detection
on COCO test-dev
gDLS*: Generalized Pose-and-Scale Estimation Given Scale and Gravity Priors
Many real-world applications in augmented reality (AR), 3D mapping, and robotics require both fast and accurate estimation of camera poses and scales from multiple images captured by multiple cameras or a single moving camera.
Few-Shot Open-Set Recognition using Meta-Learning
It is argued that the classic softmax classifier is a poor solution for open-set recognition, since it tends to overfit on the training classes.
Improving Person Re-identification with Iterative Impression Aggregation
Not only does such a simple method improve the performance of the baseline models, it also achieves comparable performance with latest advanced re-ranking methods.
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision.
Ranked #12 on
Weakly Supervised Action Localization
on THUMOS14
Vocal Bursts Valence Prediction
Weakly Supervised Action Localization
+2
Passport-aware Normalization for Deep Model Protection
Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification.
LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud-based Deep Networks
To overcome these shortcomings, this paper proposes a novel label guided adversarial network (LG-GAN) for real-time flexible targeted point cloud attack.
Efficient Semantic Image Synthesis via Class-Adaptive Normalization
Spatially-adaptive normalization (SPADE) is remarkably successful recently in conditional semantic image synthesis \cite{park2019semantic}, which modulates the normalized activation with spatially-varying transformations learned from semantic layouts, to prevent the semantic information from being washed away.
Practical Order Attack in Deep Ranking
The objective of this paper is to formalize and practically implement a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order of a selected set of candidates according to a permutation vector predefined by the attacker, with only limited interference to other unrelated candidates.
Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels.
Deep Model Intellectual Property Protection via Deep Watermarking
By jointly training the target model and watermark embedding, the extra barrier can even be absorbed into the target model.
Practical Relative Order Attack in Deep Ranking
In this paper, we formulate a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates.
Diverse Semantic Image Synthesis via Probability Distribution Modeling
In this paper, we propose a novel diverse semantic image synthesis framework from the perspective of semantic class distributions, which naturally supports diverse generation at semantic or even instance level.
Ranked #1 on
Image-to-Image Translation
on ADE20K Labels-to-Photos
(LPIPS metric)
Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas
By the proposed physical regularization, our method can generate HDRs which are not only visually appealing but also physically plausible.
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS’14
Video Polyp Segmentation
Weakly Supervised Action Localization
+2
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context.
Action Recognition
Weakly-supervised Temporal Action Localization
+1
SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Meanwhile, we use a sparse directed temporal graph to model the motion tendency, thus to facilitate the prediction based on the observed direction.
E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion
This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks.
Sparse Pose Trajectory Completion
In the absence of dense pose sampling in image space, these latent space trajectories provide cross-modal guidance for learning.
Breadcrumbs: Adversarial Class-Balanced Sampling for Long-tailed Recognition
It is shown that, unlike class-balanced sampling, this is an adversarial augmentation strategy.
GistNet: a Geometric Structure Transfer Network for Long-Tailed Recognition
A new learning algorithm is then proposed for GeometrIc Structure Transfer (GIST), with resort to a combination of loss functions that combine class-balanced and random sampling to guarantee that, while overfitting to the popular classes is restricted to geometric parameters, it is leveraged to transfer class geometry from popular to few-shot classes.
Semi-supervised Long-tailed Recognition using Alternate Sampling
A consistency loss has been introduced to limit the impact from unlabeled data while leveraging them to update the feature embedding.
Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking
In this paper, we propose a novel online approach to learning the pose dynamics, which are independent of pose detections in current fame, and hence may serve as a robust estimation even in challenging scenarios including occlusion.
Multi-Person Pose Estimation
Multi-Person Pose Estimation and Tracking
+1
Adversarial Attack and Defense in Deep Ranking
In this paper, we propose two attacks against deep ranking systems, i. e., Candidate Attack and Query Attack, that can raise or lower the rank of chosen candidates by adversarial perturbations.
Video Imprint
In the proposed framework, a dedicated feature alignment module is incorporated for redundancy removal across frames to produce the tensor representation, i. e., the video imprint.
Learning View Selection for 3D Scenes
Efficient 3D space sampling to represent an underlying3D object/scene is essential for 3D vision, robotics, and be-yond.
SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction
Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians.
Enriching Local and Global Contexts for Temporal Action Localization
We explore two existing models to be the P-Net in our experiments.
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.
Poison Ink: Robust and Invisible Backdoor Attack
As the image structure can keep its semantic meaning during the data transformation, such trigger pattern is inherently robust to data transformations.
Exploring Structure Consistency for Deep Model Watermarking
However, little attention has been devoted to the protection of DNNs in image processing tasks.
DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval
Many previous methods on text-based person retrieval tasks are devoted to learning a latent common space mapping, with the purpose of extracting modality-invariant features from both visual and textual modality.
Ranked #6 on
Text based Person Retrieval
on RSTPReid
Weakly-guided Self-supervised Pretraining for Temporal Activity Detection
However, such pretrained models are not ideal for downstream detection, due to the disparity between the pretraining and the downstream fine-tuning tasks.
Ranked #3 on
Action Detection
on Charades
Robust Pose Estimation in Crowded Scenes with Direct Pose-Level Inference
Instead of inferring individual keypoints, the Pose-level Inference Network (PINet) directly infers the complete pose cues for a person from his/her visible body parts.
Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning
The most popular and accessible 3D representation, i. e., point clouds, involves discrete samples of the underlying continuous 3D surface.
Ranked #5 on
3D Point Cloud Linear Classification
on ModelNet40
(using extra training data)
3D Point Cloud Classification
3D Point Cloud Linear Classification
+3
Progressive Backdoor Erasing via connecting Backdoor and Adversarial Attacks
Deep neural networks (DNNs) are known to be vulnerable to both backdoor attacks as well as adversarial attacks.
E^2TAD: An Energy-Efficient Tracking-based Action Detector
Video action detection (spatio-temporal action localization) is usually the starting point for human-centric intelligent analysis of videos nowadays.
Social Interpretable Tree for Pedestrian Trajectory Prediction
Understanding the multiple socially-acceptable future behaviors is an essential task for many vision applications.
PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition
Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbations.
Exploring Discrete Diffusion Models for Image Captioning
The image captioning task is typically realized by an auto-regressive method that decodes the text tokens one by one.
Boosted Dynamic Neural Networks
To optimize the model, these prediction heads together with the network backbone are trained on every batch of training data.
DDM-NET: End-to-end learning of keypoint feature Detection, Description and Matching for 3D localization
In this paper, we propose an end-to-end framework that jointly learns keypoint detection, descriptor representation and cross-frame matching for the task of image-based 3D localization.
Sparse Instance Conditioned Multimodal Trajectory Prediction
Specifically, SICNet learns comprehensive sparse instances, i. e., representative points of the future trajectory, through a mask generated by a long short-term memory encoder and uses the memory mechanism to store and retrieve such sparse instances.
Trajectory Unified Transformer for Pedestrian Trajectory Prediction
Pedestrian trajectory prediction is an essentially connecting link to understanding human behavior.
Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization
To this end, we propose a unified framework, termed Noisy Pseudo-Label Learning, to handle both location biases and category errors.
Parallel Attention Interaction Network for Few-Shot Skeleton-Based Action Recognition
Learning discriminative features from very few labeled samples to identify novel classes has received increasing attention in skeleton-based action recognition.
Diversity-Aware Meta Visual Prompting
We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone.
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.
Regularizing Second-Order Influences for Continual Learning
Continual learning aims to learn on non-stationary data streams without catastrophically forgetting previous knowledge.
Designing a Better Asymmetric VQGAN for StableDiffusion
The training cost of our asymmetric VQGAN is cheap, and we only need to retrain a new asymmetric decoder while keeping the vanilla VQGAN encoder and StableDiffusion unchanged.
HQ-50K: A Large-scale, High-quality Dataset for Image Restoration
This paper introduces a new large-scale image restoration dataset, called HQ-50K, which contains 50, 000 high-quality images with rich texture details and semantic diversity.
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
Based on our analysis, we provide a simple yet effective way to boost the adversarial robustness of MAE.
SOAR: Scene-debiasing Open-set Action Recognition
The former prevents the decoder from reconstructing the video background given video features, and thus helps reduce the background information in feature learning.
Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorance
First, prediction uncertainty should be separately quantified as confusion depicting inter-class uncertainties and ignorance identifying out-of-distribution samples.
HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending
Even though they can enable very fine-grained local control, such interaction modes are inefficient for the editing conditions that can be easily specified by language descriptions or reference images.
Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception
Active recognition enables robots to intelligently explore novel observations, thereby acquiring more information while circumventing undesired viewing conditions.
Sparse Pedestrian Character Learning for Trajectory Prediction
Specifically, TSNet learns the negative-removed characters in the sparse character representation stream to improve the trajectory embedding obtained in the trajectory representation stream.
UGG: Unified Generative Grasping
Generation-based methods that generate grasping postures conditioned on the object can often produce diverse grasping, but they are insufficient for high grasping success due to lack of discriminative information.
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS).
Jailbreaking Attack against Multimodal Large Language Model
This paper focuses on jailbreaking attacks against multi-modal large language models (MLLMs), seeking to elicit MLLMs to generate objectionable responses to harmful user queries.
Deployment Prior Injection for Run-time Calibratable Object Detection
With a strong alignment between the training and test distributions, object relation as a context prior facilitates object detection.
Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction
Previous studies have tried to tackle this problem by leveraging a portion of the trajectory data from the target domain to adapt the model.
Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes
To this end, we first devise innovative strategies to adaptively select high-quality positive and negative classes from the label space, by modeling both the confidence and rank of a class in relation to those of the target class.
Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
We hypothesize that the latent representation learned from a pretrained generative T2V model encapsulates rich semantics and coherent temporal correspondences, thereby naturally facilitating video understanding.
Referring Video Object Segmentation
Semantic Segmentation
+2
Transformer based Pluralistic Image Completion with Reduced Information Loss
The indices of quantized pixels are used as tokens for the inputs and prediction targets of the transformer.
