Search Results for author:
Found 45 papers, 22 papers with code
Exploring Interpretability for Visual Prompt Tuning with Hierarchical Concepts
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks.
VoLUT: Efficient Volumetric streaming enhanced by LUT-based super-resolution
A natural approach to mitigate the bandwidth issue is to reduce the volumetric video's data rate by downsampling the content prior to transmission.
Real-Time Neural-Enhancement for Online Cloud Gaming
To address this, we introduce River, a cloud gaming delivery framework designed based on the observation that video segment features in cloud gaming are typically repetitive and redundant.
HPT++: Hierarchically Prompting Vision-Language Models with Multi-Granularity Knowledge Generation and Improved Structure Modeling
Specifically, we introduce a relationship-guided attention module to capture pair-wise associations among entities and attributes for low-level prompt learning.
Ranked #1 on
Prompt Engineering
on ImageNet V2
ActPrompt: In-Domain Feature Adaptation via Action Cues for Video Temporal Grounding
Video temporal grounding is an emerging topic aiming to identify specific clips within videos.
DiffPhysBA: Diffusion-based Physical Backdoor Attack against Person Re-Identification in Real-World
Consequently, DiffPhysBA can generate realistic attributes as semantic-level triggers in the digital domain and provides higher physical ASR compared to the direct paste method by 25. 6% on the real-world test set.
Compression-Realized Deep Structural Network for Video Quality Enhancement
This paper focuses on the task of quality enhancement for compressed videos.
LLM-RadJudge: Achieving Radiologist-Level Evaluation for X-Ray Report Generation
This study proposes a novel evaluation framework using large language models (LLMs) to compare radiology reports for assessment.
Understanding and Improving Training-free Loss-based Diffusion Guidance
Adding additional control to pretrained diffusion models has become an increasingly popular research area, with extensive applications in computer vision, reinforcement learning, and AI for science.
Disentangled Prompt Representation for Domain Generalization
Although there is a growing focus on VFM-based domain prompt tuning for DG effectively learning prompts that disentangle invariant features across all domains remains a major challenge.
DreamDistribution: Learning Prompt Distribution for Diverse In-distribution Generation
We introduce a solution that allows a pretrained T2I diffusion model to learn a set of soft prompts, enabling the generation of novel images by sampling prompts from the learned distribution.
Learning Hierarchical Prompt with Structured Linguistic Knowledge for Vision-Language Models
To address this limitation and prioritize harnessing structured knowledge, this paper advocates for leveraging LLMs to build a graph for each description to model the entities and attributes describing the category, as well as their correlations.
Ranked #2 on
Prompt Engineering
on ImageNet V2
Unified Medical Image Pre-training in Language-Guided Common Semantic Space
To overcome the aforementioned challenges, we propose an Unified Medical Image Pre-training framework, namely UniMedI, which utilizes diagnostic reports as common semantic space to create unified representations for diverse modalities of medical images (especially for 2D and 3D images).
Online Video Quality Enhancement with Spatial-Temporal Look-up Tables
To the best of our knowledge, we are the first to exploit the LUT structure to extract temporal information in video tasks.
AccFlow: Backward Accumulation for Long-Range Optical Flow
To train and evaluate the proposed AccFlow, we have constructed a large-scale high-quality dataset named CVO, which provides ground-truth optical flow labels between adjacent and distant frames.
Content-Adaptive Auto-Occlusion Network for Occluded Person Re-Identification
To address these challenges, we propose a novel Content-Adaptive Auto-Occlusion Network (CAAO), that is able to dynamically select the proper occlusion region of an image based on its content and the current training status.
Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models
Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content, opening up the opportunity to improve image super-resolution (SR) tasks.
EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search Benchmark
The energy consumption for training deep learning models is increasing at an alarming rate due to the growth of training data and model scale, resulting in a negative impact on carbon neutrality.
SIMPLE: Specialized Model-Sample Matching for Domain Generalization
Moreover, our method is highly efficient and achieves more than 1000 times training speedup compared to the conventional DG methods with fine-tuning a pretrained model.
Ranked #1 on
Domain Generalization
on PACS
Online Streaming Video Super-Resolution with Convolutional Look-Up Table
To facilitate the research on this problem, a new benchmark dataset named LDV-WebRTC is constructed based on a real-world online streaming system.
Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism
Correspondingly, we propose a Dual Stream deep model for Stereotypical Behaviours Detection, DS-SBD, based on the temporal trajectory of human poses and the repetition patterns of human actions.
Towards Inference Efficient Deep Ensemble Learning
Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e. g., can be up to 2048X in large-scale ensemble tasks.
Human Co-Parsing Guided Alignment for Occluded Person Re-identification
Most supervised methods propose to train an extra human parsing model aside from the ReID model with cross-domain human parts annotation, suffering from expensive annotation cost and domain gap; Unsupervised methods integrate a feature clustering-based human parsing process into the ReID model, but lacking supervision signals brings less satisfactory segmentation results.
Ranked #9 on
Person Re-Identification
on Occluded-DukeMTMC
Attentive Mask CLIP
To address this issue, we propose an attentive token removal approach for CLIP training, which retains tokens with a high semantic correlation to the text description.
Learning Domain Invariant Prompt for Vision-Language Models
Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples.
Ranked #5 on
Prompt Engineering
on Food-101
Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification
Instead of learning fixed triggers for the target classes from the training set, DT-IBA can dynamically generate new triggers for any unknown identities.
Online Video Super-Resolution with Convolutional Kernel Bypass Graft
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
Towards Privacy-Preserving Person Re-identification via Person Identify Shift
In this paper, we aim to develop a technique that can achieve a good trade-off between privacy protection and data usability for person ReID.
RendNet: Unified 2D/3D Recognizer With Latent Space Rendering
Instead of looking at one format, it is a good solution to utilize the formats of VG and RG together to avoid these shortcomings.
Privacy-preserving Online AutoML for Domain-Specific Face Detection
Thanks to HyperFD, each local task (client) is able to effectively leverage the learning "experience" of previous tasks without uploading raw images to the platform; meanwhile, the meta-feature extractor is continuously learned to better trade off the bias and variance.
Domain Generalization using Pretrained Models without Fine-tuning
Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks.
Ranked #10 on
Domain Generalization
on TerraIncognita
Recognizing Vector Graphics without Rasterization
In this paper, we consider a different data format for images: vector graphics.
SANE: Specialization-Aware Neural Network Ensemble
Real-world data is often generated by some complex distribution, which can be approximated by a composition of multiple simpler distributions.
Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change.
Learning 3D Shape Feature for Texture-Insensitive Person Re-Identification
In this paper, rather than relying on texture based information, we propose to improve the robustness of person ReID against clothing texture by exploiting the information of a person's 3D shape.
Ranked #4 on
Person Re-Identification
on VC-Clothes
Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query
However, the performance of existing methods suffers in real life since the user is likely to provide an incomplete description of an image, which often leads to results filled with false positives that fit the incomplete description.
Contextual Non-Local Alignment over Full-Scale Representation for Text-Based Person Search
Secondly, a BERT with locality-constrained attention is proposed to obtain representations of descriptions at different scales.
Ranked #17 on
Text based Person Retrieval
on CUHK-PEDES
Learning To Know Where To See: A Visibility-Aware Approach for Occluded Person Re-Identification
Several mainstream methods utilize extra cues (e. g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem.
Ranked #24 on
Person Re-Identification
on Occluded-DukeMTMC
One for More: Selecting Generalizable Samples for Generalizable ReID Model
Current training objectives of existing person Re-IDentification (ReID) models only ensure that the loss of the model decreases on selected training batch, with no regards to the performance on samples outside the batch.
Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
Specifically, we construct a positive clip and a negative clip for each video.
Devil's in the Details: Aligning Visual Clues for Conditional Embedding in Person Re-Identification
Secondly, the Conditional Feature Embedding requires the overall feature of a query image to be dynamically adjusted based on the gallery image it matches, while most of the existing methods ignore the reference images.
Ranked #1 on
Person Re-Identification
on CUHK03-C
Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians
In the conventional person Re-ID setting, it is widely assumed that cropped person images are for each individual.
Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification
Instead of one subspace for each viewpoint, our method projects the feature from different viewpoints into a unified hypersphere and effectively models the feature distribution on both the identity-level and the viewpoint-level.
Ranked #7 on
Person Re-Identification
on DukeMTMC-reID
(using extra training data)
Rethinking Temporal Fusion for Video-based Person Re-identification on Semantic and Time Aspect
Recently, the research interest of person re-identification (ReID) has gradually turned to video-based methods, which acquire a person representation by aggregating frame features of an entire video.
Pyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Most existing Re-IDentification (Re-ID) methods are highly dependent on precise bounding boxes that enable images to be aligned with each other.
Ranked #2 on
Person Re-Identification
on CUHK03-C
