Search Results for author:
Found 51 papers, 32 papers with code
Retrieval-Augmented Open-Vocabulary Object Detection
Specifically, RALF consists of two modules: Retrieval Augmented Losses (RAL) and Retrieval-Augmented visual Features (RAF).
Ranked #9 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
Prompt Learning via Meta-Regularization
Recently, prompt learning approaches have been explored to efficiently and effectively adapt the vision-language models to a variety of downstream tasks.
Ranked #2 on
Prompt Engineering
on Stanford Cars
Groupwise Query Specialization and Quality-Aware Multi-Assignment for Transformer-based Visual Relationship Detection
Groupwise Query Specialization trains a specialized query by dividing queries and relations into disjoint groups and directing a query in a specific query group solely toward relations in the corresponding relation group.
Ranked #1 on
Scene Graph Generation
on Visual Genome
vid-TLDR: Training Free Token merging for Light-weight Video Transformer
To tackle these issues, we propose training free token merging for lightweight video Transformer (vid-TLDR) that aims to enhance the efficiency of video Transformers by merging the background tokens without additional training.
Ranked #2 on
Video Retrieval
on SSv2-template retrieval
(using extra training data)
Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers
Here, we argue that token fusion needs to consider diverse relations between tokens to minimize information loss.
Ranked #1 on
Efficient ViTs
on ImageNet-1K (With LV-ViT-S)
Stochastic Conditional Diffusion Models for Semantic Image Synthesis
This facilitates the generation of an image close to a clean image, enabling robust generation.
DDMI: Domain-Agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
Arguably, this architecture limits the expressive power of generative models and results in low-quality INR generation.
Ranked #2 on
Video Generation
on Sky Time-lapse
UnionDet: Union-Level Detector Towards Real-Time Human-Object Interaction Detection
This is a major bottleneck in HOI detection inference time.
Graph-Guided Reasoning for Multi-Hop Question Answering in Large Language Models
Specifically, we first leverage LLMs to construct a "question/rationale graph" by using knowledge extraction prompting given the initial question and the rationales generated in the previous steps.
UP-NeRF: Unconstrained Pose-Prior-Free Neural Radiance Fields
Neural Radiance Field (NeRF) has enabled novel view synthesis with high fidelity given images and camera poses.
Large Language Models are Temporal and Causal Reasoners for Video Question Answering
We observe that the LLMs provide effective priors in exploiting $\textit{linguistic shortcuts}$ for temporal and causal reasoning in Video Question Answering (VideoQA).
Ranked #1 on
Video Question Answering
on TVQA
Distribution-Aware Prompt Tuning for Vision-Language Models
Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data.
Read-only Prompt Optimization for Vision-Language Few-shot Learning
RPO leverages masked attention to prevent the internal representation shift in the pre-trained model.
Ranked #6 on
Prompt Engineering
on Caltech-101
Semantic-Aware Implicit Template Learning via Part Deformation Consistency
In this paper, we highlight the importance of part deformation consistency and propose a semantic-aware implicit template learning framework to enable semantically plausible deformation.
Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classification
However, those methods do not consider whether a concept is visually relevant or not, which is an important factor in computing meaningful concept scores.
Open-vocabulary Video Question Answering: A New Benchmark for Evaluating the Generalizability of Video Question Answering Models
We hence propose a new benchmark, Open-vocabulary Video Question Answering (OVQA), to measure the generalizability of VideoQA models by considering rare and unseen answers.
Ranked #8 on
Visual Question Answering (VQA)
on MSRVTT-QA
Self-positioning Point-based Transformer for Point Cloud Understanding
In this paper, we present a Self-Positioning point-based Transformer (SPoTr), which is designed to capture both local and global shape contexts with reduced complexity.
Ranked #2 on
3D Part Segmentation
on ShapeNet-Part
MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models
Therefore, we propose MEta Loss TRansformer (MELTR), a plug-in module that automatically and non-linearly combines various loss functions to aid learning the target task via auxiliary learning.
Ranked #2 on
Video Captioning
on YouCook2
k-SALSA: k-anonymous synthetic averaging of retinal images via local style alignment
While prior works have explored image de-identification strategies based on synthetic averaging of images in other domains (e. g. facial images), existing techniques face difficulty in preserving both privacy and clinical utility in retinal images, as we demonstrate in our work.
Semantic-aware Occlusion Filtering Neural Radiance Fields in the Wild
We present a learning framework for reconstructing neural scene representations from a small number of unconstrained tourist photos.
Robust Camera Pose Refinement for Multi-Resolution Hash Encoding
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF.
Domain Generalization Emerges from Dreaming
Recent studies have proven that DNNs, unlike human vision, tend to exploit texture information rather than shape.
Relation-Aware Language-Graph Transformer for Question Answering
To address these issues, we propose Question Answering Transformer (QAT), which is designed to jointly reason over language and graphs with respect to entity relations in a unified manner.
Invertible Monotone Operators for Normalizing Flows
Normalizing flows model probability distributions by learning invertible transformations that transfer a simple distribution into complex distributions.
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for Transformers
To this end, we propose TokenMixup, an efficient attention-guided token-level data augmentation method that aims to maximize the saliency of a mixed set of tokens.
Ranked #65 on
Image Classification
on CIFAR-10
SageMix: Saliency-Guided Mixup for Point Clouds
Mixup is a simple and widely-used data augmentation technique that has proven effective in alleviating the problems of overfitting and data scarcity.
Ranked #40 on
3D Part Segmentation
on ShapeNet-Part
Deformable Graph Transformer
Transformer-based models have recently shown success in representation learning on graph-structured data beyond natural language processing and computer vision.
Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Prediction
Graph Neural Networks (GNNs) have been widely applied to various fields for learning over graph-structured data.
Consistency Learning via Decoding Path Augmentation for Transformers in Human Object Interaction Detection
Motivated by various inference paths for HOI detection, we propose cross-path consistency learning (CPC), which is a novel end-to-end learning strategy to improve HOI detection for transformers by leveraging augmented decoding paths.
Ranked #1 on
Human-Object Interaction Detection
on V-COCO
(MAP metric)
Video-Text Representation Learning via Differentiable Weak Temporal Alignment
In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW).
Metropolis-Hastings Data Augmentation for Graph Neural Networks
We also propose a simple and effective semi-supervised learning strategy with generated samples from MH-Aug. Our extensive experiments demonstrate that MH-Aug can generate a sequence of samples according to the target distribution to significantly improve the performance of GNNs.
Improving Object Detection, Multi-object Tracking, and Re-Identification for Disaster Response Drones
In the second approach, although DeepSORT only processes a quarter of all frames due to hardware and time limitations, our model with DeepSORT (42. 9%) outperforms FairMOT (71. 4%) in terms of recall.
Deformable Graph Convolutional Networks
To address the two common problems of graph convolution, in this paper, we propose Deformable Graph Convolutional Networks (Deformable GCNs) that adaptively perform convolution in multiple latent spaces and capture short/long-range dependencies between nodes.
Ranked #3 on
Node Classification on Non-Homophilic (Heterophilic) Graphs
on Cornell (48%/32%/20% fixed splits)
Node Classification on Non-Homophilic (Heterophilic) Graphs
Representation Learning
Point Cloud Augmentation with Weighted Local Transformations
Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less explored in the point cloud literature.
Ranked #11 on
Point Cloud Classification
on PointCloud-C
Graph Transformer Networks: Learning Meta-path Graphs to Improve GNNs
Despite the success of GNNs, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs.
HOTR: End-to-End Human-Object Interaction Detection with Transformers
Human-Object Interaction (HOI) detection is a task of identifying "a set of interactions" in an image, which involves the i) localization of the subject (i. e., humans) and target (i. e., objects) of interaction, and ii) the classification of the interaction labels.
Ranked #16 on
Human-Object Interaction Detection
on V-COCO
Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
Our method is learning to learn a primary task with various auxiliary tasks to improve generalization performance.
Robust Neural Networks inspired by Strong Stability Preserving Runge-Kutta methods
Motivated by the SSP property and a generalized Runge-Kutta method, we propose Strong Stability Preserving networks (SSP networks) which improve robustness against adversarial attacks.
Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
Our proposed method is learning to learn a primary task by predicting meta-paths as auxiliary tasks.
Unpaired Image Translation via Adaptive Convolution-based Normalization
Disentangling content and style information of an image has played an important role in recent success in image translation.
Graph Transformer Networks
In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve identifying useful connections between unconnected nodes on the original graph, while learning effective node representation on the new graphs in an end-to-end fashion.
ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
It boosts the representational power by modeling, in a high dimensional space, interdependency of channels between a depthwise convolution layer and a projection layer in the ANTBlocks.
Efficient Relative Attribute Learning using Graph Neural Networks
A sizable body of work on relative attributes provides compelling evidence that relating pairs of images along a continuum of strength pertaining to a visual attribute yields significant improvements in a wide variety of tasks in vision.
Tensorize, Factorize and Regularize: Robust Visual Relationship Learning
Visual relationships provide higher-level information of objects and their relations in an image â this enables a semantic understanding of the scene and helps downstream applications.
Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families
There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make.
Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification
Multi-label classification is the task of predicting a set of labels for a given input instance.
Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective
Recent results in coupled or temporal graphical models offer schemes for estimating the relationship structure between features when the data come from related (but distinct) longitudinal sources.
Riemannian Nonlinear Mixed Effects Models: Analyzing Longitudinal Deformations in Neuroimaging
Statistical machine learning models that operate on manifold-valued data are being extensively studied in vision, motivated by applications in activity recognition, feature tracking and medical imaging.
Latent Variable Graphical Model Selection Using Harmonic Analysis: Applications to the Human Connectome Project (HCP)
A major goal of imaging studies such as the (ongoing) Human Connectome Project (HCP) is to characterize the structural network map of the human brain and identify its associations with covariates such as genotype, risk factors, and so on that correspond to an individual.
Interpolation on the Manifold of K Component GMMs
Probability density functions (PDFs) are fundamental "objects" in mathematics with numerous applications in computer vision, machine learning and medical imaging.
Multivariate General Linear Models (MGLM) on Riemannian Manifolds with Applications to Statistical Analysis of Diffusion Weighted Images
Linear regression is a parametric model which is ubiquitous in scientific analysis.
