Search Results for author:
Found 45 papers, 18 papers with code
Case-Enhanced Vision Transformer: Improving Explanations of Image Similarity with a ViT-based Similarity Metric
This short paper presents preliminary research on the Case-Enhanced Vision Transformer (CEViT), a similarity measurement method aimed at improving the explainability of similarity assessments for image data.
Transformer for Object Re-Identification: A Survey
Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from varying viewpoints.
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge.
Situated Cameras, Situated Knowledges: Towards an Egocentric Epistemology for Computer Vision
In her influential 1988 paper, Situated Knowledges, Donna Haraway uses vision and perspective as a metaphor to discuss scientific knowledge.
A Tensor-based Convolutional Neural Network for Small Dataset Classification
Inspired by the ConvNets with structured hidden representations, we propose a Tensor-based Neural Network, TCNN.
SePaint: Semantic Map Inpainting via Multinomial Diffusion
Prediction beyond partial observations is crucial for robots to navigate in unknown environments because it can provide extra information regarding the surroundings beyond the current sensing range or resolution.
LoCoNet: Long-Short Context Network for Active Speaker Detection
These two contexts are complementary to each other and can help infer the active speaker.
VindLU: A Recipe for Effective Video-and-Language Pretraining
Furthermore, our model also obtains state-of-the-art video question-answering results on ActivityNet-QA, MSRVTT-QA, MSRVTT-MC and TVQA.
Ranked #2 on
Video Retrieval
on Condensed Movies
(using extra training data)
Attention is All They Need: Exploring the Media Archaeology of the Computer Vision Research Paper
In this work, we examine the effects of this growth from a media archaeology perspective, through the changes to figures and tables in research papers.
Action Recognition based on Cross-Situational Action-object Statistics
We set out to identify properties of training data that lead to action recognition models with greater generalization ability.
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i. e., the point cloud videos.
Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition
One-shot fine-grained visual recognition often suffers from the problem of having few training examples for new fine-grained classes.
Controlling the Quality of Distillation in Response-Based Network Compression
We argue that for a given teacher-student pair, the quality of distillation can be improved by finding the sweet spot between batch size and number of epochs while training the teacher.
Error Diagnosis of Deep Monocular Depth Estimation Models
To address errors in depth estimation, we introduce a novel Depth Error Detection Network (DEDN) that spatially identifies erroneous depth predictions in the monocular depth estimation models.
Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments.
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Features
Given a pair of cases, the CDH approach attributes the difference in their solutions to the difference in the problems they solve, and generates adaptation rules to adjust solutions accordingly when a retrieved case and new query have similar problem differences.
A Survey on Deep Learning Technique for Video Segmentation
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing.
Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers
We analyze egocentric views of attended objects from infants.
How to Accelerate Capsule Convolutions in Capsule Networks
How to improve the efficiency of routing procedures in CapsNets has been studied a lot.
Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning
We present a novel technique for self-supervised video representation learning by: (a) decoupling the learning objective into two contrastive subtasks respectively emphasizing spatial and temporal features, and (b) performing it hierarchically to encourage multi-scale understanding.
Whose hand is this? Person Identification from Egocentric Hand Gestures
But while one's own face is not frequently visible, their hands are: in fact, hands are among the most common objects in one's own field of view.
Deep Tiered Image Segmentation For Detecting Internal Ice Layers in Radar Imagery
Understanding the structure of Earth's polar ice sheets is important for modeling how global warming will impact polar ice and, in turn, the Earth's climate.
A Computational Model of Early Word Learning from the Infant's Point of View
Human infants have the remarkable ability to learn the associations between object names and visual objects from inherently ambiguous experiences.
When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos
A new spatial-temporal area under curve (STAUC) evaluation metric is proposed and used with DoTA.
HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation
Hand-object pose estimation (HOPE) aims to jointly detect the poses of both a hand and of a held object.
Interaction Graphs for Object Importance Estimation in On-road Driving Videos
A vehicle driving along the road is surrounded by many objects, but only a small subset of them influence the driver's decisions and actions.
Learning Video Object Segmentation from Unlabeled Videos
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data.
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
P-CapsNets: a General Form of Convolutional Neural Networks
The experiment shows that P-CapsNets achieve better performance than CapsNets with varied routing procedures by using significantly fewer parameters on MNIST\&CIFAR10.
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
One-shot fine-grained visual recognition often suffers from the problem of training data scarcity for new fine-grained classes.
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+2
A Self Validation Network for Object-Level Human Attention Estimation
Due to the foveated nature of the human vision system, people can focus their visual attention on a small region of their visual field at a time, which usually contains only a single object.
Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study
Inspired by the remarkable ability of the infant visual learning system, a recent study collected first-person images from children to analyze the `training data' that they receive.
Embodied Visual Recognition
Passive visual systems typically fail to recognize objects in the amodal setting where they are heavily occluded.
Unsupervised Domain Adaptation using Generative Models and Self-ensembling
The results suggest that selfensembling is better than simple data augmentation with the newly generated data and a single model trained this way can have the best performance across all different transfer tasks.
Toddler-Inspired Visual Object Learning
Real-world learning systems have practical limitations on the quality and quantity of the training datasets that they can collect and consider.
Generalized Capsule Networks with Trainable Routing Procedure
To overcome this disadvantages of current routing procedures in CapsNet, we embed the routing procedure into the optimization procedure with all other parameters in neural networks, namely, make coupling coefficients in the routing procedure become completely trainable.
Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting
Detecting small, densely distributed objects is a significant challenge: small objects often contain less distinctive information compared to larger ones, and finer-grained precision of bounding box boundaries are required.
Using Artificial Tokens to Control Languages for Multilingual Image Caption Generation
Recent work in computer vision has yielded impressive results in automatically describing images with natural language.
A Hybrid Supervised-unsupervised Method on Image Topic Visualization with Convolutional Neural Network and LDA
Given the progress in image recognition with recent data driven paradigms, it's still expensive to manually label a large training data to fit a convolutional neural network (CNN) model.
A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks
CNNs eliminate the need for manually designing features and separation rules, but require a large amount of annotated training data.
Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models
We observe that our method consistently outperforms BS and previously proposed techniques for diverse decoding from neural sequence models.
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
Many practical perception systems exist within larger processes that include interactions with users or additional components capable of evaluating the quality of predicted solutions.
Sentiment/Subjectivity Analysis Survey for Languages other than English
This paper surveys different ways used for building systems for subjective and sentiment analysis for languages other than English.
Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
Convolutional Neural Networks have achieved state-of-the-art performance on a wide range of tasks.
