Search Results for author:
Found 113 papers, 30 papers with code
FlexNeRF: Photorealistic Free-viewpoint Rendering of Moving Humans from Sparse Views
We present FlexNeRF, a method for photorealistic freeviewpoint rendering of humans in motion from monocular videos.
Fighting Malicious Media Data: A Survey on Tampering Detection and Deepfake Detection
Online media data, in the forms of images and videos, are becoming mainstream communication channels.
TAG: Boosting Text-VQA via Text-aware Visual Question-answer Generation
To address this deficiency, we develop a new method to generate high-quality and diverse QA pairs by explicitly utilizing the existing rich text available in the scene context of each image.
InvGAN: Invertible GANs
Our \textbf{InvGAN}, short for Invertible GAN, successfully embeds real images to the latent space of a high quality generative model.
Learning Graphs for Knowledge Transfer With Limited Labels
The standard paradigm is to utilize relationships in the input graph to transfer information using GCNs from training to testing nodes in the graph; for example, the semi-supervised, zero-shot, and few-shot learning setups.
Rethinking Pseudo Labels for Semi-Supervised Object Detection
In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels.
Ranked #5 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision.
Box-supervised Instance Segmentation
Semantic correspondence
+1
Learned Spatial Representations for Few-shot Talking-Head Synthesis
In contrast, we propose to factorize the representation of a subject into its spatial and style components.
THAT: Two Head Adversarial Training for Improving Robustness at Scale
Many variants of adversarial training have been proposed, with most research focusing on problems with relatively few classes.
Scale Normalized Image Pyramids with AutoFocus for Object Detection
The resulting algorithm is referred to as AutoFocus and results in a 2. 5-5 times speed-up during inference when used with SNIP.
Deep Video Inpainting Detection
This paper studies video inpainting detection, which localizes an inpainted region in a video both spatially and temporally.
Multimodal Attention for Layout Synthesis in Diverse Domains
We address the problem of scene layout generation for diverse domains such as images, mobile applications, documents and 3D objects.
2D or not 2D? Adaptive 3D Convolution Selection for Efficient Video Recognition
Then, only frames and convolutions that are selected by the selection network are used in the 3D model to generate predictions.
Ranked #10 on
Action Recognition
on ActivityNet
SLADE: A Self-Training Framework For Distance Metric Learning
We first train a teacher model on the labeled data and use it to generate pseudo labels for the unlabeled data.
All About Knowledge Graphs for Actions
Current action recognition systems require large amounts of training data for recognizing an action.
Ranked #12 on
Zero-Shot Action Recognition
on Kinetics
InfoFocus: 3D Object Detection for Autonomous Driving with Dynamic Information Modeling
Results show that our framework achieves the state-of-the-art performance with 31 FPS and improves our baseline significantly by 9. 0% mAP on the nuScenes test set.
Ranked #319 on
3D Object Detection
on nuScenes
DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes
In contrast, we propose a general-purpose method that works on both indoor and outdoor scenes.
SaccadeNet: A Fast and Accurate Object Detector
Object detection is an essential step towards holistic scene understanding.
Ranked #206 on
Object Detection
on COCO test-dev
DeepStrip: High Resolution Boundary Refinement
In this paper, we target refining the boundaries in high resolution images given low resolution masks.
Depth Completion Using a View-constrained Deep Prior
Given color images and noisy and incomplete target depth maps, we optimize a randomly-initialized CNN model to reconstruct a depth map restored by virtue of using the CNN network structure as a prior combined with a view-constrained photo-consistency loss.
Recognizing Instagram Filtered Images with Feature De-stylization
Deep neural networks have been shown to suffer from poor generalization when small perturbations are added (like Gaussian noise), yet little work has been done to evaluate their robustness to more natural image transformations like photo filters.
Fashion Outfit Complementary Item Retrieval
We evaluate our method on the outfit compatibility, FITB and new retrieval tasks.
Learning from Noisy Anchors for One-stage Object Detection
State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth objects.
LiteEval: A Coarse-to-Fine Framework for Resource Efficient Video Recognition
This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios.
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
Active learning (AL) combines data labeling and model training to minimize the labeling cost by prioritizing the selection of high value data that can best improve model performance.
Consistency-Based Semi-Supervised Active Learning: Towards Minimizing Labeling Budget
Active learning (AL) aims to integrate data labeling and model training in a unified way, and to minimize the labeling budget by prioritizing the selection of high value data that can best improve model performance.
Cross-X Learning for Fine-Grained Visual Categorization
Recognizing objects from subcategories with very subtle differences remains a challenging task due to the large intra-class and small inter-class variation.
Ranked #15 on
Fine-Grained Image Classification
on NABirds
(using extra training data)
Fine-Grained Image Classification
Fine-Grained Visual Categorization
HiCoRe: Visual Hierarchical Context-Reasoning
To do so, we build and apply graphs to graph convolution networks with convolutional neural networks.
WSLLN: Weakly Supervised Natural Language Localization Networks
We propose weakly supervised language localization networks (WSLLN) to detect events in long, untrimmed videos given language queries.
Truncated Cauchy Non-negative Matrix Factorization
Non-negative matrix factorization (NMF) minimizes the Euclidean distance between the data matrix and its low rank approximation, and it fails when applied to corrupted data because the loss function is sensitive to outliers.
Efficient Object Embedding for Spliced Image Retrieval
Detecting spliced images is one of the emerging challenges in computer vision.
Adversarial Training for Free!
Adversarial training, in which a network is trained on adversarial examples, is one of the few defenses against adversarial attacks that withstands strong attacks.
ACE: Adapting to Changing Environments for Semantic Segmentation
However, neural classifiers are often extremely brittle when confronted with domain shift---changes in the input distribution that occur over time.
An Analysis of Pre-Training on Object Detection
We analyze how well their features generalize to tasks like image classification, semantic segmentation and object detection on small datasets like PASCAL-VOC, Caltech-256, SUN-397, Flowers-102 etc.
Referring to Objects in Videos using Spatio-Temporal Identifying Descriptions
This paper presents a new task, the grounding of spatio-temporal identifying descriptions in videos.
M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots.
StartNet: Online Detection of Action Start in Untrimmed Videos
We propose StartNet to address Online Detection of Action Start (ODAS) where action starts and their associated categories are detected in untrimmed, streaming videos.
Compatible and Diverse Fashion Image Inpainting
The latent representations are jointly optimized with the corresponding generation network to condition the synthesis process, encouraging a diverse set of generated results that are visually compatible with existing fashion garments.
TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition
We present Temporal Aggregation Network (TAN) which decomposes 3D convolutions into spatial and temporal aggregation blocks.
FA-RPN: Floating Region Proposals for Face Detection
We propose a novel approach for generating region proposals for performing face-detection.
AutoFocus: Efficient Multi-Scale Inference
Instead of processing an entire image pyramid, AutoFocus adopts a coarse to fine approach and only processes regions which are likely to contain small objects at finer scales.
MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment
In this paper, we present Moment Alignment Network (MAN), a novel framework that unifies the candidate moment encoding and temporal structural reasoning in a single-shot feed-forward network.
AdaFrame: Adaptive Frame Selection for Fast Video Recognition
We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition.
Universal Adversarial Training
Standard adversarial attacks change the predicted class label of a selected image by adding specially tailored small perturbations to its pixels.
Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation
We show results on CAD120 (which provides pre-computed node features and edge weights for fair performance comparison across algorithms) as well as a more complex real-world activity dataset, Charades.
Generate, Segment and Refine: Towards Generic Manipulation Segmentation
The advent of image sharing platforms and the easy availability of advanced photo editing software have resulted in a large quantities of manipulated images being shared on the internet.
Explicit Bias Discovery in Visual Question Answering Models
It is of interest to the community to explicitly discover such biases, both for understanding the behavior of such models, and towards debugging them.
Modeling Local Geometric Structure of 3D Point Clouds using Geo-CNN
This encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy.
Temporal Recurrent Networks for Online Action Detection
Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed.
Ranked #6 on
Online Action Detection
on TVSeries
Improving Annotation for 3D Pose Dataset of Fine-Grained Object Categories
Existing 3D pose datasets of object categories are limited to generic object types and lack of fine-grained information.
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior
Video summarization is a challenging under-constrained problem because the underlying summary of a single video strongly depends on users' subjective understandings.
Soft Sampling for Robust Object Detection
Interestingly, we observe that after dropping 30% of the annotations (and labeling them as background), the performance of CNN-based object detectors like Faster-RCNN only drops by 5% on the PASCAL VOC dataset.
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
An Analysis of Scale Invariance in Object Detection  SNIP
On the COCO dataset, our single model performance is 45. 7% and an ensemble of 3 networks obtains an mAP of 48. 3%.
SNIPER: Efficient Multi-Scale Training
Our implementation based on Faster-RCNN with a ResNet-101 backbone obtains an mAP of 47. 6% on the COCO dataset for bounding box detection and can process 5 images per second during inference with a single GPU.
Ranked #117 on
Object Detection
on COCO test-dev
Learning Rich Features for Image Manipulation Detection
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned.
Stacked U-Nets: A No-Frills Approach to Natural Image Segmentation
Many imaging tasks require global information about all pixels in an image.
DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation
In particular, given an image from the source domain and unlabeled samples from the target domain, the generator synthesizes new images on-the-fly to resemble samples from the target domain in appearance and the segmentation network further refines high-level features before predicting semantic maps, both of which leverage feature statistics of sampled images from the target domain.
Layout-induced Video Representation for Recognizing Agent-in-Place Actions
We address the recognition of agent-in-place actions, which are associated with agents who perform them and places where they occur, in the context of outdoor home surveillance.
Two-Stream Neural Networks for Tampered Face Detection
We propose a two-stream network for face tampering detection.
ReMotENet: Efficient Relevant Motion Event Detection for Large-scale Home Surveillance Videos
To dramatically speedup relevant motion event detection and improve its performance, we propose a novel network for relevant motion event detection, ReMotENet, which is a unified, end-to-end data-driven method using spatial-temporal attention-based 3D ConvNets to jointly model the appearance and motion of objects-of-interest in a video.
Deception Detection in Videos
We present a system for covert automated deception detection in real-life courtroom trial videos.
R-FCN-3000 at 30fps: Decoupling Detection and Classification
Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization.
VITON: An Image-based Virtual Try-on Network
We present an image-based VIirtual Try-On Network (VITON) without using 3D information in any form, which seamlessly transfers a desired clothing item onto the corresponding region of a person using a coarse-to-fine strategy.
An Analysis of Scale Invariance in Object Detection - SNIP
On the COCO dataset, our single model performance is 45. 7% and an ensemble of 3 networks obtains an mAP of 48. 3%.
Ranked #132 on
Object Detection
on COCO test-dev
BlockDrop: Dynamic Inference Paths in Residual Networks
Very deep convolutional neural networks offer excellent recognition results, yet their computational expense limits their impact for many real-world applications.
NISP: Pruning Networks using Neuron Importance Score Propagation
In contrast, we argue that it is essential to prune neurons in the entire neuron network jointly based on a unified goal: minimizing the reconstruction error of important responses in the "final response layer" (FRL), which is the second-to-last layer before classification, for a pruned network to retrain its predictive power.
C-WSL: Count-guided Weakly Supervised Localization
We introduce count-guided weakly supervised localization (C-WSL), an approach that uses per-class object count as a new form of supervision to improve weakly supervised localization (WSL).
Dynamic Zoom-in Network for Fast Object Detection in Large Images
We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images.
On Encoding Temporal Evolution for Real-time Action Prediction
Anticipating future actions is a key component of intelligence, specifically when it applies to real-time systems, such as robots or autonomous cars.
Temporal Context Network for Activity Localization in Videos
For each temporal segment inside a proposal, features are uniformly sampled at a pair of scales and are input to a temporal convolutional neural network for classification.
Ranked #7 on
Action Recognition
on THUMOS’14
Automatic Spatially-aware Fashion Concept Discovery
This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites.
Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation
Understanding visual relationships involves identifying the subject, the object, and a predicate relating them.
Learning Fashion Compatibility with Bidirectional LSTMs
To this end, we propose to jointly learn a visual-semantic embedding and the compatibility relationships among fashion items in an end-to-end fashion.
FASON: First and Second Order Information Fusion Network for Texture Recognition
We then build a multi-level deep architecture to exploit the first and second order information within different convolutional layers.
Soft-NMS -- Improving Object Detection With One Line of Code
To this end, we propose Soft-NMS, an algorithm which decays the detection scores of all other objects as a continuous function of their overlap with M. Hence, no object is eliminated in this process.
Weakly-Supervised Spatial Context Networks
In particular, we propose spatial context networks that learn to predict a representation of one image patch from another image patch, within the same image, conditioned on their real-valued relative spatial offset.
Fast-AT: Fast Automatic Thumbnail Generation using Deep Neural Networks
It is a fully-convolutional deep neural network, which learns specific filters for thumbnails of different sizes and aspect ratios.
Generalized Deep Image to Image Regression
We present a Deep Convolutional Neural Network architecture which serves as a generic image-to-image regressor that can be trained end-to-end without any further machinery.
ActionFlowNet: Learning Motion Representation for Action Recognition
Even with the recent advances in convolutional neural networks (CNN) in various visual recognition tasks, the state-of-the-art action recognition system still relies on hand crafted motion feature such as optical flow to achieve the best performance.
Ranked #66 on
Action Recognition
on HMDB-51
Learning a Discriminative Filter Bank within a CNN for Fine-grained Recognition
Compared to earlier multistage frameworks using CNN features, recent end-to-end deep approaches for fine-grained recognition essentially enhance the mid-level learning capability of CNNs.
Ranked #20 on
Fine-Grained Image Classification
on CUB-200-2011
Generating Holistic 3D Scene Abstractions for Text-based Image Retrieval
Since interactions between objects can be reduced to a limited set of atomic spatial relations in 3D, we study the possibility of inferring 3D structure from a text description rather than an image, applying physical relation models to synthesize holistic 3D abstract object layouts satisfying the spatial constraints present in a textual description.
ModelHub: Towards Unified Data and Lifecycle Management for Deep Learning
Deep learning modeling lifecycle generates a rich set of data artifacts, such as learned parameters and training logs, and comprises of several frequently conducted tasks, e. g., to understand the model behaviors and to try out new models.
Fused DNN: A deep neural network fusion approach to fast and robust pedestrian detection
A single shot deep convolutional network is trained as a object detector to generate all possible pedestrian candidates of different sizes and occlusions.
Ranked #19 on
Pedestrian Detection
on Caltech
The Role of Context Selection in Object Detection
We investigate the reasons why context in object detection has limited utility by isolating and evaluating the predictive power of different context cues under ideal conditions in which context provided by an oracle.
Modeling Context Between Objects for Referring Expression Understanding
Our approach uses an LSTM to learn the probability of a referring expression, with input features from a region and a context region.
Mining Discriminative Triplets of Patches for Fine-Grained Classification
Fine-grained classification involves distinguishing between similar sub-categories based on subtle differences in highly localized regions; therefore, accurate localization of discriminative regions remains a major challenge.
Scalable Gaussian Processes for Supervised Hashing
We propose a flexible procedure for large-scale image search by hash functions with kernels.
Supervised Incremental Hashing
In the first stage of classification, binary codes are considered as class labels by a set of binary SVMs; each corresponds to one bit.
Learning Temporal Regularity in Video Sequences
Perceiving meaningful activities in a long video sequence is a challenging problem due to ambiguous definition of 'meaningfulness' as well as clutters in the scene.
Ranked #2 on
Traffic Accident Detection
on A3D
Generating Discriminative Object Proposals via Submodular Ranking
Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation.
Parameterizing Region Covariance: An Efficient Way To Apply Sparse Codes On Second Order Statistics
Sparse representations have been successfully applied to signal processing, computer vision and machine learning.
G-CNN: an Iterative Grid Based Object Detector
G-CNN starts with a multi-scale grid of fixed bounding boxes.
Action Recognition with Image Based CNN Features
Action recognition tasks usually relies on complex handcrafted structures as features to represent the human action model.
VRFP: On-the-fly Video Retrieval using Web Images and Fast Fisher Vector Products
VRFP is a real-time video retrieval framework based on short text input queries, which obtains weakly labeled training images from the web after the query is known.
Multi-Task Learning With Low Rank Attribute Embedding for Person Re-Identification
Since attributes are generally correlated, we introduce a low rank attribute embedding into the MTL formulation to embed original binary attributes to a continuous attribute space, where incorrect and incomplete attributes are rectified and recovered to better describe people.
Selective Encoding for Recognizing Unreliably Localized Faces
Most existing face verification systems rely on precise face detection and registration.
Searching for Objects using Structure in Indoor Scenes
However, we can use structure in the scene to search for objects without processing the entire image.
Selecting Relevant Web Trained Concepts for Automated Event Retrieval
Given a text description of an event, event retrieval is performed by selecting concepts linguistically related to the event description and fusing the concept responses on unseen videos.
On Large-Scale Retrieval: Binary or n-ary Coding?
To make large-scale search feasible, Distance Estimation and Subset Indexing are the main approaches.
Class Consistent Multi-Modal Fusion With Binary Features
Many existing recognition algorithms combine different modalities based on training accuracy but do not consider the possibility of noise at test time.
Exploiting Local Features from Deep Networks for Image Retrieval
Deep convolutional neural networks have been successfully applied to image classification tasks.
SHOE: Supervised Hashing with Output Embeddings
We present a supervised binary encoding scheme for image retrieval that learns projections by taking into account similarity between classes obtained from output embeddings.
A Probabilistic Framework for Multimodal Retrieval using Integrative Indian Buffet Process
We propose a multimodal retrieval procedure based on latent feature models.
Comparing apples to apples in the evaluation of binary coding methods
We discuss methodological issues related to the evaluation of unsupervised binary code construction methods for nearest neighbor search.
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images.
Planar Structure Matching Under Projective Uncertainty for Geolocation
Image based geolocation aims to answer the question: where was this ground photograph taken?
Representing Videos Using Mid-level Discriminative Patches
representation for videos based on mid-level discriminative spatio-temporal patches.
Adding Unlabeled Samples to Categories by Learned Attributes
We propose a method to expand the visual coverage of training sets that consist of a small number of labeled examples using learned attributes.
Learning Structured Low-Rank Representations for Image Classification
An approach to learn a structured low-rank representation for image classification is presented.
Submodular Salient Region Detection
The problem of salient region detection is formulated as the well-studied facility location problem from operations research.
Automatic online tuning for fast Gaussian summation
To solve the second problem, we present an online tuning approach that results in a black box method that automatically chooses the evaluation method and its parameters to yield the best performance for the input data, desired accuracy, and bandwidth.
A ``Shape Aware'' Model for semi-supervised Learning of Objects and its Context
Using an analogous reasoning, we present an approach that combines bag-of-words and spatial models to perform semantic and syntactic analysis for recognition of an object based on its internal appearance and its context.
