Search Results for author:
Found 23 papers, 8 papers with code
LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending
Scaling the number of concepts in customized generation meets a broader demand for user creation, whereas existing methods face challenges with generation quality and computational efficiency.
Twofold Debiasing Enhances Fine-Grained Learning with Coarse Labels
The Coarse-to-Fine Few-Shot (C2FS) task is designed to train models using only coarse labels, then leverages a limited number of subclass samples to achieve fine-grained recognition capabilities.
Noise May Contain Transferable Knowledge: Understanding Semi-supervised Heterogeneous Domain Adaptation from an Empirical Perspective
Based on this insight, we perform a series of experiments to uncover the underlying principles of transferable knowledge in SHDA.
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
In this paper, we explore the idea that CV adopts discrete and terminological task definitions (\eg, ``image segmentation''), which may be a key barrier to zero-shot task generalization.
Customized Generation Reimagined: Fidelity and Editability Harmonized
Customized generation aims to incorporate a novel concept into a pre-trained text-to-image model, enabling new generations of the concept in novel contexts guided by textual prompts.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
Rethinking Guidance Information to Utilize Unlabeled Samples:A Label Encoding Perspective
By analyzing the learning objective of ERM, we find that the guidance information for labeled samples in a specific category is the corresponding label encoding.
Enhancing Event Causality Identification with Rationale and Structure-Aware Causal Question Answering
In addition, we generate the rationales to explain why these events have causal relations.
Towards Surveillance Video-and-Language Understanding: New Dataset Baselines and Challenges
Furthermore we benchmark SOTA models for four multimodal tasks on this newly created dataset which serve as new baselines for surveillance VALU.
Semantic Lens: Instance-Centric Semantic Alignment for Video Super-Resolution
As a critical clue of video super-resolution (VSR), inter-frame alignment significantly impacts overall performance.
Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges
Furthermore, we benchmark SOTA models for four multimodal tasks on this newly created dataset, which serve as new baselines for surveillance video-and-language understanding.
GAN-based Image Compression with Improved RDO Process
GAN-based image compression schemes have shown remarkable progress lately due to their high perceptual quality at low bit rates.
The First Comprehensive Dataset with Multiple Distortion Types for Visual Just-Noticeable Differences
To benefit JND modeling, this work establishes a generalized JND dataset with a coarse-to-fine JND selection, which contains 106 source images and 1, 642 JND maps, covering 25 distortion types.
JND-Based Perceptual Optimization For Learned Image Compression
After combining them together, we can better assign the distortion in the compressed image with the guidance of JND to preserve the high perceptual quality.
HVS-Inspired Signal Degradation Network for Just Noticeable Difference Estimation
However, they have a major drawback that the generated JND is assessed in the real-world signal domain instead of in the perceptual domain in the human brain.
Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation
To achieve this, an adversarial loss is firstly proposed to make the deep learning models attacked by the adversarial images successfully.
CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction
Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document.
Full RGB Just Noticeable Difference (JND) Modelling
Besides, the JND of the red and blue channels are larger than that of the green one according to the experimental results of the proposed model, which demonstrates that more changes can be tolerated in the red and blue channels, in line with the well-known fact that the human visual system is more sensitive to the green channel in comparison with the red and blue ones.
Auto-Weighted Layer Representation Based View Synthesis Distortion Estimation for 3-D Video Coding
Experimental results show that the VSD can be accurately estimated with the weights learnt by the nonlinear mapping function once its associated S-VSDs are available.
A New Image Codec Paradigm for Human and Machine Uses
Meanwhile, an image predictor is designed and trained to achieve the general-quality image reconstruction with the 16-bit gray-scale profile and signal features.
Just Noticeable Difference for Deep Machine Vision
Experimental results on image classification demonstrate that we successfully find the JND for deep machine vision.
A C++ library for Multimodal Deep Learning
MDL, Multimodal Deep Learning Library, is a deep learning framework that supports multiple models, and this document explains its philosophy and functionality.
