Search Results for author:
Found 60 papers, 27 papers with code
SPAN: Spatial Pyramid Attention Network for Image Manipulation Localization
Tehchniques for manipulating images are advancing rapidly; while these are helpful for many useful tasks, they also pose a threat to society with their ability to create believable misinformation.
Ranked #7 on
Image Manipulation Detection
on CocoGlide
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models
Large-scale pretrained vision-language models like CLIP have demonstrated remarkable zero-shot image classification capabilities across diverse domains.
GaitSTR: Gait Recognition with Sequential Two-stream Refinement
We demonstrate that with refined skeletons, the performance of the gait recognition model can achieve further improvement on public gait recognition datasets compared with state-of-the-art methods without extra annotations.
Ranked #2 on
Multiview Gait Recognition
on CASIA-B
SEAS: ShapE-Aligned Supervision for Person Re-Identification
When recognizing an individual's identity existing methods primarily rely on appearance which can be influenced by the background environment due to a lack of body shape awareness.
Large Language Models are Good Prompt Learners for Low-Shot Image Classification
Thus, we propose LLaMP, Large Language Models as Prompt learners, that produces adaptive prompts for the CLIP text encoder, establishing it as the connecting bridge.
CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering
Generalizability and few-shot learning are key challenges in Neural Radiance Fields (NeRF), often due to the lack of a holistic understanding in pixel-level rendering.
ShARc: Shape and Appearance Recognition for Person Identification In-the-wild
PSE encodes the body shape via binarized silhouettes, skeleton motions, and 3-D body shape, while AAE provides two levels of temporal appearance feature aggregation: attention-based feature aggregation and averaging aggregation.
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation
Large-scale Pre-Training Vision-Language Model such as CLIP has demonstrated outstanding performance in zero-shot classification, e. g. achieving 76. 3% top-1 accuracy on ImageNet without seeing any example, which leads to potential benefits to many tasks that have no labeled data.
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts.
GaitRef: Gait Recognition with Refined Sequential Skeletons
Two common modalities used for representing the walking sequence of a person are silhouettes and joint skeletons.
Ranked #5 on
Multiview Gait Recognition
on CASIA-B
CAT-NeRF: Constancy-Aware Tx$^2$Former for Dynamic Body Modeling
This paper addresses the problem of human rendering in the video with temporal appearance constancy.
Efficient Feature Distillation for Zero-shot Annotation Object Detection
We propose a new setting for detecting unseen objects called Zero-shot Annotation object Detection (ZAD).
Gait Recognition Using 3-D Human Body Shape Inference
Gait recognition, which identifies individuals based on their walking patterns, is an important biometric technique since it can be observed from a distance and does not require the subject's cooperation.
PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch
Despite the diversity in attack patterns, adversarial patches tend to be highly textured and different in appearance from natural images.
MixNorm: Test-Time Adaptation Through Online Normalization Estimation
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples.
SimMER: Simple Maximization of Entropy and Rank for Self-supervised Representation Learning
With both entropy and rank maximization, our method surpasses the state-of-the-art on CIFAR-10 and Mini-ImageNet under the standard linear evaluation protocol.
Testing-Time Adaptation through Online Normalization Estimation
We present a simple and effective way to estimate the batch-norm statistics during test time, to fast adapt a source model to target test samples.
Video Question Answering with Phrases via Semantic Roles
Video Question Answering (VidQA) evaluation metrics have been limited to a single-word answer or selecting a phrase from a fixed set of phrases.
Visual Semantic Role Labeling for Video Understanding
We propose a new framework for understanding and representing related salient events in a video using visual semantic role labeling.
SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification
Combining the Pair Loss with the techniques developed by the MixMatch family, our proposed SimPLE algorithm shows significant performance gains over previous algorithms on CIFAR-100 and Mini-ImageNet, and is on par with the state-of-the-art methods on CIFAR-10 and SVHN.
Utilizing Every Image Object for Semi-supervised Phrase Grounding
The annotated language queries available during training are limited, which also limits the variations of language combinations that a model can see during training.
SPAN: Spatial Pyramid Attention Network forImage Manipulation Localization
We present a novel framework, Spatial Pyramid Attention Network (SPAN) for detection and localization of multiple types of image manipulations.
Visually Grounded Continual Learning of Compositional Phrases
To study this human-like language acquisition ability, we present VisCOLL, a visually grounded language learning task, which simulates the continual acquisition of compositional phrases from streaming visual scenes.
CPARR: Category-based Proposal Analysis for Referring Relationships
The task of referring relationships is to localize subject and object entities in an image satisfying a relationship query, which is given in the form of \texttt{<subject, predicate, object>}.
Video Object Grounding using Semantic Roles in Language Description
We explore the task of Video Object Grounding (VOG), which grounds objects in videos referred to in natural language descriptions.
Curriculum DeepSDF
When learning to sketch, beginners start with simple and flexible shapes, and then gradually strive for more complex and accurate ones in the subsequent training sessions.
Zero-Shot Grounding of Objects from Natural Language Queries
A phrase grounding system localizes a particular object in an image referred to by a natural language query.
Pose-variant 3D Facial Attribute Generation
We address the challenging problem of generating facial attributes using a single image in an unconstrained pose.
Activity Driven Weakly Supervised Object Detection
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models.
Ranked #1 on
Weakly Supervised Object Detection
on Charades
PIRC Net : Using Proposal Indexing, Relationships and Context for Phrase Grounding
Phrase Grounding aims to detect and localize objects in images that are referred to and are queried by natural language phrases.
NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
Comparing to standard Faster RCNN, it contains three highlights: an ensemble of two classification heads and a distillation head to avoid overfitting on noisy labels and improve the mining precision, masking the negative sample loss in box predictor to avoid the harm of false negative labels, and training box regression head only on seed annotations to eliminate the harm from inaccurate boundaries of mined bounding boxes.
MAC: Mining Activity Concepts for Language-based Temporal Localization
Previous methods address the problem by considering features from video sliding windows and language queries and learning a subspace to encode their correlation, which ignore rich semantic cues about activities in videos and queries.
Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
Performance on the five tasks of depth estimation, optical flow estimation, odometry, moving object segmentation and scene flow estimation shows that our approach outperforms other SoTA methods.
CTAP: Complementary Temporal Action Proposal Generation
Temporal action proposal generation is an important task, akin to object proposals, temporal action proposals are intended to capture "clips" or temporal intervals in videos that are likely to contain an action.
Ranked #10 on
Temporal Action Proposal Generation
on ActivityNet-1.3
Every Pixel Counts: Unsupervised Geometry Learning with Holistic 3D Motion Understanding
The four types of information, i. e. 2D flow, camera pose, segment mask and depth maps, are integrated into a differentiable holistic 3D motion parser (HMP), where per-pixel 3D motion for rigid background and moving objects are recovered.
Revisiting Temporal Modeling for Video-based Person ReID
Although many methods on temporal modeling have been proposed, it is hard to directly compare these methods, because the choice of feature extractor and loss function also have a large impact on the final performance.
Motion-Appearance Co-Memory Networks for Video Question Answering
Specifically, there are three salient aspects: (1) a co-memory attention mechanism that utilizes cues from both motion and appearance to generate attention; (2) a temporal conv-deconv network to generate multi-level contextual facts; (3) a dynamic fact ensemble method to construct temporal representation dynamically for different questions.
Ranked #31 on
Visual Question Answering (VQA)
on MSRVTT-QA
LEGO: Learning Edge with Geometry all at Once by Watching Videos
In our framework, the predicted depths, normals and edges are forced to be consistent all the time.
Knowledge Aided Consistency for Weakly Supervised Phrase Grounding
In this paper, we explore the consistency contained in both visual and language modalities, and leverage complementary external knowledge to facilitate weakly supervised grounding.
ExpNet: Landmark-Free, Deep, 3D Facial Expressions
Our ExpNet CNN is applied directly to the intensities of a face image and regresses a 29D vector of 3D expression coefficients.
Ranked #1 on
3D Facial Expression Recognition
on 2017_test set
(using extra training data)
Knowledge Concentration: Learning 100K Object Classifiers in a Single CNN
To address these challenges, we propose a Knowledge Concentration method, which effectively transfers the knowledge from dozens of specialists (multiple teacher networks) into one single model (one student network) to classify 100K object categories.
FacePoseNet: Making a Case for Landmark-Free Face Alignment
Instead, we compare our FPN with existing methods by evaluating how they affect face recognition accuracy on the IJB-A and IJB-B benchmarks: using the same recognition pipeline, but varying the face alignment method.
Ranked #1 on
Facial Landmark Detection
on 300W
(Mean Error Rate metric)
Query-guided Regression Network with Context Policy for Phrase Grounding
Given a textual description of an image, phrase grounding localizes objects in the image referred by query phrases in the description.
Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation
In this work, we address the problem of spatio-temporal action detection in temporally untrimmed videos.
RED: Reinforced Encoder-Decoder Networks for Action Anticipation
RED takes multiple history representations as input and learns to anticipate a sequence of future representations.
TALL: Temporal Activity Localization via Language Query
For evaluation, we adopt TaCoS dataset, and build a new dataset for this task on top of Charades by adding sentence temporal annotations, called Charades-STA.
Cascaded Boundary Regression for Temporal Action Detection
CBR uses temporal coordinate regression to refine the temporal boundaries of the sliding windows.
Ranked #6 on
Temporal Action Localization
on THUMOS’14
(mAP IOU@0.1 metric)
AMC: Attention guided Multi-modal Correlation Learning for Image Search
According to the intent of query, attention mechanism can be introduced to adaptively balance the importance of different modalities.
TURN TAP: Temporal Unit Regression Network for Temporal Action Proposals
Temporal Action Proposal (TAP) generation is an important problem, as fast and accurate extraction of semantically important (e. g. human actions) segments from untrimmed videos is an important step for large-scale video analysis.
Ranked #8 on
Action Recognition
on THUMOS’14
A Multi-Scale Cascade Fully Convolutional Network Face Detector
The number of proposals is decreased after each level, and the areas of regions are decreased to more precisely fit the face.
Learning Action Concept Trees and Semantic Alignment Networks from Image-Description Data
Besides, the action categories in such datasets are pre-defined and vocabularies are fixed.
ACD: Action Concept Discovery from Image-Sentence Corpora
It obtains candidate action concepts by extracting verb-object pairs from sentences and verifies their visualness with the associated images.
Face Recognition Using Deep Multi-Pose Representations
In our representation, a face image is processed by several pose-specific deep convolutional neural network (CNN) models to generate multiple pose-specific features.
Ranked #14 on
Face Verification
on IJB-A
ABC-CNN: An Attention Based Convolutional Neural Network for Visual Question Answering
ABC-CNN determines an attention map for an image-question pair by convolving the image feature map with configurable convolutional kernels derived from the question's semantics.
ProNet: Learning to Propose Object-specific Boxes for Cascaded Neural Networks
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations.
Ranked #5 on
Weakly Supervised Object Detection
on MS COCO
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.
DISCOVER: Discovering Important Segments for Classification of Video Events and Recounting
Our goal is to find the important segments and capture their information for event classification and recounting.
Efficient Detector Adaptation for Object Detection in a Video
In this work, we present a novel and efficient detector adaptation method which improves the performance of an offline trained classifier (baseline classifier) by adapting it to new test datasets.
