Search Results for author:
Found 25 papers, 9 papers with code
Towards Real-World Adverse Weather Image Restoration: Enhancing Clearness and Semantics with Vision-Language Models
For clearness enhancement, we use real-world data, utilizing a dual-step strategy with pseudo-labels assessed by vision-language models and weather prompt learning.
EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture
The motion module can be adapted to various DiT baseline methods to generate video with different styles.
Unveiling the Generalization Power of Fine-Tuned Large Language Models
While Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, fine-tuning these models on downstream, domain-specific datasets is often necessary to yield superior performance on test sets compared to their counterparts without fine-tuning.
Slot-VLM: SlowFast Slots for Video-Language Modeling
A pivotal challenge is the development of an efficient method to encapsulate video content into a set of representative tokens to align with LLMs.
Near-Field Communications: A Comprehensive Survey
This evolution is giving rise to the emergence of near-field communications (NFC) in future wireless systems.
A Survey of Reasoning with Foundation Models
Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-world settings such as negotiation, medical diagnosis, and criminal investigation.
Retrieval-based Video Language Model for Efficient Long Video Question Answering
To address these issues, we introduce a simple yet effective retrieval-based video language model (R-VLM) for efficient and interpretable long video QA.
EasyPhoto: Your Smart AI Photo Generator
By training a digital doppelganger of a specific user ID using 5 to 20 relevant images, the finetuned model (according to the trained LoRA model) allows for the generation of AI photos using arbitrary templates.
FaceChain: A Playground for Human-centric Artificial Intelligence Generated Content
In this paper, we present FaceChain, a personalized portrait generation framework that combines a series of customized image-generation model and a rich set of face-related perceptual understanding models (\eg, face detection, deep face embedding extraction, and facial attribute recognition), to tackle aforementioned challenges and to generate truthful personalized portraits, with only a handful of portrait images as input.
MRecGen: Multimodal Appropriate Reaction Generator
Verbal and non-verbal human reaction generation is a challenging task, as different reactions could be appropriate for responding to the same behaviour.
Shape Guided Gradient Voting for Domain Generalization
In this work, with the assumption that the gradients of a specific domain samples under the classification task could also reflect the property of the domain, we propose a Shape Guided Gradient Voting (SGGV) method for domain generalization.
Video Dehazing via a Multi-Range Temporal Alignment Network with Physical Prior
Video dehazing aims to recover haze-free frames with high visibility and contrast.
MuLTI: Efficient Video-and-Language Understanding with Text-Guided MultiWay-Sampler and Multiple Choice Modeling
Specifically, we design a Text-Guided MultiWay-Sampler based on adapt-pooling residual mapping and self-attention modules to sample long sequences and fuse multi-modal features, which reduces the computational costs and addresses performance degradation caused by previous samplers.
Ranked #1 on
TGIF-Transition
on TGIF-QA
(using extra training data)
Active Simultaneously Transmitting and Reflecting (STAR)-RISs: Modelling and Analysis
The amplitude gains of the STAR element are derived for both coupled and independent phase-shift scenarios.
Exploiting STAR-RISs in Near-Field Communications
Exploiting the electric current distribution, a Green's function method based channel model is proposed.
Simultaneously Transmitting and Reflecting (STAR)-RISs: Are they Applicable to Dual-Sided Incidence?
A hardware model and a signal model are proposed for dual-sided simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs), where the signal simultaneously incident on both sides of the surface.
Two-stage Temporal Modelling Framework for Video-based Depression Recognition using Graph Representation
The short-term depressive behaviour modelling stage first deep learns depression-related facial behavioural features from multiple short temporal scales, where a Depression Feature Enhancement (DFE) module is proposed to enhance the depression-related clues for all temporal scales and remove non-depression noises.
SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning
Ten learning-based surgical tasks are built in the platform, which are common in the real autonomous surgical execution.
Simultaneously Transmitting and Reflecting (STAR) Intelligent Omni-Surfaces, Their Modeling and Implementation
With the rapid development of advanced electromagnetic manipulation technologies, researchers and engineers are starting to study smart surfaces that can achieve enhanced coverages, high reconfigurability, and are easy to deploy.
STAR-RISs: Simultaneous Transmitting and Reflecting Reconfigurable Intelligent Surfaces
In this letter, simultaneous transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) are studied.
Reconfigurable Intelligent Surface-assisted Networks: Phase Alignment Categories
The reconfigurable intelligent surface (RIS) is one of the promising technology contributing to the next generation smart radio environment.
A Novel Physics-based Channel Model for Reconfigurable Intelligent Surface-assisted Multi-user Communication Systems
A novel physics-based RIS channel model is proposed.
Reconfigurable Intelligent Surfaces: Principles and Opportunities
In this context, we provide a comprehensive overview of the state-of-the-art on RISs, with focus on their operating principles, performance evaluation, beamforming design and resource management, applications of machine learning to RIS-enhanced wireless networks, as well as the integration of RISs with other emerging technologies.
Deep Mining External Imperfect Data for Chest X-ray Disease Screening
Recent researches have demonstrated that performance bottleneck exists in joint training on different CXR datasets, and few made efforts to address the obstacle.
IRNet: Instance Relation Network for Overlapping Cervical Cell Segmentation
In this paper, we propose a novel Instance Relation Network (IRNet) for robust overlapping cell segmentation by exploring instance relation interaction.
