Search Results for author:
Found 27 papers, 10 papers with code
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation
Extensive experiments on various kinds of visual attributes with SOTA personalization methods show the ability of the proposed method to mimic target visual appearance in novel contexts, thus improving the controllability and flexibility of personalization.
Break-for-Make: Modular Low-Rank Adaptations for Composable Content-Style Customization
Based on the adapters broken apart for separate training content and style, we then make the entity parameter space by reconstructing the content and style PLPs matrices, followed by fine-tuning the combined adapter to generate the target object with the desired appearance.
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework
We adopt a two-stage training strategy for the diffusion model, effectively binding movements with specific appearances.
FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs
However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.
Exploiting User Comments for Early Detection of Fake News Prior to Users' Commenting
To break such a dilemma, a feasible but not well-studied solution is to leverage social contexts (e. g., comments) from historical news for training a detection model and apply it to newly emerging news without social contexts.
Combating Online Misinformation Videos: Characterization, Detection, and Future Directions
With information consumption via online video streaming becoming increasingly popular, misinformation video poses a new threat to the health of the online information ecosystem.
Improving Fake News Detection of Influential Domain via Domain- and Instance-Level Transfer
To address this issue, we propose a Domain- and Instance-level Transfer Framework for Fake News Detection (DITFEND), which could improve the performance of specific target domains.
Delving into the Frequency: Temporally Consistent Human Motion Transfer in the Fourier Space
To close the frequency gap between the natural and synthetic videos, we propose a novel Frequency-based human MOtion TRansfer framework, named FreMOTR, which can effectively mitigate the spatial artifacts and the temporal inconsistency of the synthesized videos.
Characterizing Multi-Domain False News and Underlying User Effects on Chinese Weibo
False news that spreads on social media has proliferated over the past years and has led to multi-aspect threats in the real world.
A Prompting-based Approach for Adversarial Example Generation and Robustness Enhancement
Our attack technique targets the inherent vulnerabilities of NLP models, allowing us to generate samples even without interacting with the victim NLP model, as long as it is based on pre-trained language models (PLMs).
DRAG: Dynamic Region-Aware GCN for Privacy-Leaking Image Detection
However, these methods have two limitations: 1) they neglect other important elements like scenes, textures, and objects beyond the capacity of pretrained object detectors; 2) the correlation among objects is fixed, but a fixed correlation is not appropriate for all the images.
A Dual Prompt Learning Framework for Few-Shot Dialogue State Tracking
In this paper, we focus on how to utilize the language understanding and generation ability of pre-trained language models for DST.
Quantifying Robustness to Adversarial Word Substitutions
Deep-learning-based NLP models are found to be vulnerable to word substitution perturbations.
MDFEND: Multi-domain Fake News Detection
In this paper, we first design a benchmark of fake news dataset for MFND with domain label annotated, namely Weibo21, which consists of 4, 488 fake news and 4, 640 real news from 9 different domains.
DPUV3INT8: A Compiler View to programmable FPGA Inference Engines
We have a FPGA design, we make it fast, efficient, and tested for a few important examples.
The role of the cell cycle in collective cell dynamics
We develop a simple model of the cell cycle, the fundamental regulatory network controlling growth and division, and couple this to the physical forces arising within the cell collective.
Biological Physics Soft Condensed Matter
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored. In this work, we provide the first systematic analysis on the underperformance of state-of-the-art models in front of long-tail distribution.
Asymmetric GAN for Unpaired Image-to-image Translation
While in situations where two domains are asymmetric in complexity, i. e., the amount of information between two domains is different, these approaches pose problems of poor generation quality, mapping ambiguity, and model sensitivity.
Exploiting Multi-domain Visual Information for Fake News Detection
In the real world, fake-news images may have significantly different characteristics from real-news images at both physical and semantic levels, which can be clearly reflected in the frequency and pixel domain, respectively.
How to Write High-quality News on Social Network? Predicting News Quality by Mining Writing Style
SNQAM performs excellently on predicting quality, presenting interpretable quality score and giving accessible suggestions on how to improve it according to writing guidelines we referred to.
Tree-structured Kronecker Convolutional Network for Semantic Segmentation
Therefore, it can capture partial information and enlarge the receptive field of filters simultaneously without introducing extra parameters.
Style Separation and Synthesis via Generative Adversarial Networks
The S3-GAN consists of an encoder network, a generator network, and an adversarial network.
Sequential Prediction of Social Media Popularity with Deep Temporal Context Networks
With a joint embedding network, we obtain a unified deep representation of multi-modal user-post data in a common embedding space.
Scale-Adaptive Convolutions for Scene Parsing
Through adding a new scale regression layer, we can dynamically infer the position-adaptive scale coefficients which are adopted to resize the convolutional patches.
One-Shot Fine-Grained Instance Retrieval
Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR).
Deep Representation Learning with Part Loss for Person Re-Identification
The representation learning risk is evaluated by the proposed part loss, which automatically generates several parts for an image, and computes the person classification loss on each part separately.
Ranked #97 on
Person Re-Identification
on Market-1501
Task-Driven Dynamic Fusion: Reducing Ambiguity in Video Description
This paper contributes to: 1)The first in-depth study of the weakness inherent in data-driven static fusion methods for video captioning.
