Search Results for author:
Found 36 papers, 18 papers with code
MPII: Multi-Level Mutual Promotion for Inference and Interpretation
In this paper, we propose a multi-level Mutual Promotion mechanism for self-evolved Inference and sentence-level Interpretation (MPII).
Effectiveness of Self-Assessment Software to Evaluate Preclinical Operative Procedures
Class II preparation at 400{\mu}m tolerance had the smallest mean difference of 0. 41 points.
An edge detection-based deep learning approach for tear meniscus height measurement
For improved segmentation of the pupil and tear meniscus areas, the convolutional neural network Inceptionv3 was first implemented as an image quality assessment model, effectively identifying higher-quality images with an accuracy of 98. 224%.
MotionEditor: Editing Video Motion via Content-Aware Diffusion
This mechanism enables the editing branch to query the key and value from the reconstruction branch in a decoupled manner, making the editing branch retain the original background and protagonist appearance.
ART$\boldsymbol{\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models
Second, it preserves the high-fidelity generation ability of the pre-trained image diffusion models by making only minimal network modifications.
VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models
Our model can edit and translate the desired results within seconds based on user instructions.
A Survey on Video Diffusion Models
However, existing surveys mainly focus on diffusion models in the context of image generation, with few up-to-date reviews on their application in the video domain.
SimDA: Simple Diffusion Adapter for Efficient Video Generation
In this work, we propose a Simple Diffusion Adapter (SimDA) that fine-tunes only 24M out of 1. 1B parameters of a strong T2I model, adapting it to video generation in a parameter-efficient way.
Implicit Temporal Modeling with Learnable Alignment for Video Recognition
While modeling temporal information within straight through tube is widely adopted in literature, we find that simple frame alignment already provides enough essence without temporal attention.
Ranked #16 on
Action Classification
on Kinetics-400
ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules
We evaluate ChartReader on Chart-to-Table, ChartQA, and Chart-to-Text tasks, demonstrating its superiority over existing methods.
Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios
However, current works pursuing sentence-level explanations rely heavily on annotated training data, which limits the development of interpretability to only a few tasks.
All in Tokens: Unifying Output Space of Visual Tasks via Soft Token
With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well.
Ranked #14 on
Monocular Depth Estimation
on NYU-Depth V2
ResFormer: Scaling ViTs with Multi-Resolution Training
We introduce, ResFormer, a framework that is built upon the seminal idea of multi-resolution training for improved performance on a wide spectrum of, mostly unseen, testing resolutions.
SVFormer: Semi-supervised Video Transformer for Action Recognition
In this paper, we investigate the use of transformer models under the SSL setting for action recognition.
GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
In the second stage, we exploit transformer layers to unearth the potential semantic relations within both verbs and semantic roles.
Rethinking Spatial Invariance of Convolutional Networks for Object Counting
We evaluate our methods on 4 mainstream object counting networks (i. e., MCNN, CSRNet, SANet, and ResNet-50).
Ranked #1 on
Object Counting
on TRANCOS
On Data Scaling in Masked Image Modeling
Our study reveals that: (i) Masked image modeling is also demanding on larger data.
HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
Deeper Insights into the Robustness of ViTs towards Common Corruptions
With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy.
Multi-granularity Relabeled Under-sampling Algorithm for Imbalanced Data
The Tomek-Link sampling algorithm can effectively reduce the class overlap on data, remove the majority instances that are difficult to distinguish, and improve the algorithm classification accuracy.
SimMIM: A Simple Framework for Masked Image Modeling
We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks.
Representation Learning
Self-Supervised Image Classification
+1
Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning
Cross-modal correlation provides an inherent supervision for video unsupervised representation learning.
On the Connection between Local Attention and Dynamic Depth-wise Convolution
Sparse connectivity: there is no connection across channels, and each position is connected to the positions within a small local window.
Self-Supervised Learning with Swin Transformers
We are witnessing a modeling shift from CNN to Transformers in computer vision.
Ranked #75 on
Self-Supervised Image Classification
on ImageNet
Calibration of Human Driving Behavior and Preference Using Naturalistic Traffic Data
Towards this end it is necessary that we have a comprehensive modeling framework for decision-making within which human driving preferences can be inferred statistically from observed driving behaviors in realistic and naturalistic traffic settings.
Learning to Estimate Kernel Scale and Orientation of Defocus Blur with Asymmetric Coded Aperture
Consistent in-focus input imagery is an essential precondition for machine vision systems to perceive the dynamic environment.
Temporal Action Detection with Multi-level Supervision
We extensively benchmark against the baselines for SSAD and OSAD on our created data splits in THUMOS14 and ActivityNet1. 2, and demonstrate the effectiveness of the proposed UFA and IB methods.
Towards a Systematic Computational Framework for Modeling Multi-Agent Decision-Making at Micro Level for Smart Vehicles in a Smart World
To demonstrate how our approach can be applied to realistic traffic settings, we conduct a simulation experiment: to derive merging and yielding behaviors on a double-lane highway with an unexpected barrier.
Informative Dropout for Robust Representation Learning: A Shape-bias Perspective
Specifically, we discriminate texture from shape based on local self-information in an image, and adopt a Dropout-like algorithm to decorrelate the model output from the local texture.
Reinforcing Short-Length Hashing
Due to the compelling efficiency in retrieval and storage, similarity-preserving hashing has been widely applied to approximate nearest neighbor search in large-scale image retrieval.
Weakly-Supervised Action Localization by Generative Attention Modeling
By maximizing the conditional probability with respect to the attention, the action and non-action frames are well separated.
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
Self-supervised Object Motion and Depth Estimation from Video
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video.
Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting
By minimizing the mutual information, each column is guided to learn features with different image scales.
Learning Spatial Awareness to Improve Crowd Counting
Although the Maximum Excess over SubArrays (MESA) loss has been previously proposed to address the above issues by finding the rectangular subregion whose predicted density map has the maximum difference from the ground truth, it cannot be solved by gradient descent, thus can hardly be integrated into the deep learning framework.
Ranked #5 on
Crowd Counting
on WorldExpo’10
Decoupling Localization and Classification in Single Shot Temporal Action Detection
Each branch produces a set of action anchor layers by applying deconvolution to the feature maps of the main stream.
Ranked #26 on
Temporal Action Localization
on THUMOS’14
Recurrent Tubelet Proposal and Recognition Networks for Action Detection
The RTP initializes action proposals of the start frame through a Region Proposal Network and then estimates the movements of proposals in next frame in a recurrent manner.
