Search Results for author:
Found 37 papers, 4 papers with code
AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment
In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background.
Domain-Guided Masked Autoencoders for Unique Player Identification
We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification.
Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery
Precise Human Mesh Recovery (HMR) with in-the-wild data is a formidable challenge and is often hindered by depth ambiguities and reduced precision.
Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement
One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously.
NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation
As the largest open-source synthetic food dataset, NV-Synth highlights the value of physics-based simulations for enabling scalable and controllable generation of diverse photorealistic meal images to overcome data limitations and drive advancements in automated dietary assessment using computer vision.
FoodFusion: A Latent Diffusion Model for Realistic Food Image Generation
To address these limitations, we introduce FoodFusion, a Latent Diffusion model engineered specifically for the faithful synthesis of realistic food images from textual descriptions.
Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion
In Canada, prostate cancer is the most common form of cancer in men and accounted for 20% of new cancer cases for this demographic in 2022.
HiDiffusion: Unlocking High-Resolution Creativity and Efficiency in Low-Resolution Trained Diffusion Models
We introduce HiDiffusion, a tuning-free framework comprised of Resolution-Aware U-Net (RAU-Net) and Modified Shifted Window Multi-head Self-Attention (MSW-MSA) to enable pretrained large text-to-image diffusion models to efficiently generate high-resolution images (e. g. 1024$\times$1024) that surpass the training image resolution.
Confidant: Customizing Transformer-based LLMs via Collaborative Edge Training
Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks.
NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation
Dietary intake estimation plays a crucial role in understanding the nutritional habits of individuals and populations, aiding in the prevention and management of diet-related health issues.
AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training
Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training.
NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields
Thus, there is a need to dynamically optimize the neural network component of NeRFs to achieve a balance between computational complexity and specific targets for synthesis quality.
NutritionVerse: Empirical Study of Various Dietary Intake Estimation Approaches
Recent work has focused on using computer vision and machine learning to automatically estimate dietary intake from food images, but the lack of comprehensive datasets with diverse viewpoints, modalities and food annotations hinders the accuracy and realism of such methods.
Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos
To address these issues, we propose a robust keyframe identification module that extracts frames containing essential high-level information about the jersey number.
Mitigating Motion Blur for Robust 3D Baseball Player Pose Modeling for Pitch Analysis
The findings highlight the effectiveness of our method in mitigating the challenges posed by motion blur, thereby enhancing the overall quality of pose estimation.
The Model Inversion Eavesdropping Attack in Semantic Communication Systems
In recent years, semantic communication has been a popular research topic for its superiority in communication efficiency.
Transferring Knowledge for Food Image Segmentation using Transformers and Convolutions
To address these issues, two models are trained and compared, one based on convolutional neural networks and the other on Bidirectional Encoder representation for Image Transformers (BEiT).
Deep Joint Source-Channel Coding for Wireless Image Transmission with Entropy-Aware Adaptive Rate Control
Adaptive rate control for deep joint source and channel coding (JSCC) is considered as an effective approach to transmit sufficient information in scenarios with limited communication resources.
Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge
As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments.
NutritionVerse-3D: A 3D Food Model Dataset for Nutritional Intake Estimation
Unlike existing datasets, a collection of 3D models with nutritional information allow for view synthesis to create an infinite number of 2D images for any given viewpoint/camera angle along with the associated nutritional information.
NutritionVerse-Thin: An Optimized Strategy for Enabling Improved Rendering of 3D Thin Food Models
With the growth in capabilities of generative models, there has been growing interest in using photo-realistic renders of common 3D food items to improve downstream tasks such as food printing, nutrition prediction, or management of food wastage.
ShapeShift: Superquadric-based Object Pose Estimation for Robotic Grasping
To address these challenges, this paper proposes ShapeShift, a superquadric-based framework for object pose estimation that predicts the object's pose relative to a primitive shape which is fitted to the object.
Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data
ANL introduces the additional negative pseudo-label for all unlabeled data to leverage low-confidence examples.
MMRNet: Improving Reliability for Multimodal Object Detection and Segmentation for Bin Picking via Multimodal Redundancy
We also demonstrate that our MC score is a more reliability indicator for outputs during inference time compared to the model generated confidence scores that are often over-confident.
MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis
Autonomous bin picking poses significant challenges to vision-driven robotic systems given the complexity of the problem, ranging from various sensor modalities, to highly entangled object layouts, to diverse item properties and gripper types.
Demo: low-power communications based on RIS and AI for 6G
By jointly designing the hardware and software, this prototype can realize real-time 4K video transmission with much reduced power consumption.
MetaGraspNet_v0: A Large-Scale Benchmark Dataset for Vision-driven Robotic Grasping via Physics-based Metaverse Synthesis
We also propose a new layout-weighted performance metric alongside the dataset for evaluating object detection and segmentation performance in a manner that is more appropriate for robotic grasp applications compared to existing general-purpose performance metrics.
FTPipeHD: A Fault-Tolerant Pipeline-Parallel Distributed Training Framework for Heterogeneous Edge Devices
Our numerical results demonstrate that FTPipeHD is 6. 8x faster in training than the state of the art method when the computing capacity of the best device is 10x greater than the worst one.
Low Resolution Information Also Matters: Learning Multi-Resolution Representations for Person Re-Identification
As a prevailing task in video surveillance and forensics field, person re-identification (re-ID) aims to match person images captured from non-overlapped cameras.
TIPCB: A Simple but Effective Part-based Convolutional Baseline for Text-based Person Search
Text-based person search is a sub-task in the field of image retrieval, which aims to retrieve target person images according to a given textual description.
Ranked #11 on
Text based Person Retrieval
on CUHK-PEDES
Reference-Aided Part-Aligned Feature Disentangling for Video Person Re-Identification
Due to the inaccurate person detections and pose changes, pedestrian misalignment significantly increases the difficulty of feature extraction and matching.
Quantization in Relative Gradient Angle Domain For Building Polygon Estimation
In this paper, we leverage the performance of CNNs, and propose a module that uses prior knowledge of building corners to create angular and concise building polygons from CNN segmentation outputs.
Plant Stem Segmentation Using Fast Ground Truth Generation
Analysis of the shape of plants can potentially be used to accurately quantify the degree of wilting.
A Voice Interactive Multilingual Student Support System using IBM Watson
The chatbot could also be adapted for use in other application areas such as student info-centers, government kiosks, and mental health support systems.
Estimating Phenotypic Traits From UAV Based RGB Imagery
Use of imagery is becoming popular for phenotyping.
Locating Objects Without Bounding Boxes
In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects.
Ranked #1 on
Object Localization
on Mall
