Search Results for author:
Found 58 papers, 19 papers with code
Enabling Heterogeneous Adversarial Transferability via Feature Permutation Attacks
To address this, we propose Feature Permutation Attack (FPA), a zero-FLOP, parameter-free method that enhances adversarial transferability across diverse architectures.
TransiT: Transient Transformer for Non-line-of-sight Videography
High frame rates, for example, can be achieved by reducing either per-point scanning time or scanning density, but at the cost of lowering the information density at individual frames.
Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models.
RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control
Recent advancements in camera-trajectory-guided image-to-video generation offer higher precision and better support for complex camera control compared to text-based approaches.
WisdomBot: Tuning Large Language Models with Artificial Intelligence Knowledge
Large language models (LLMs) have emerged as powerful tools in natural language processing (NLP), showing a promising future of artificial generated intelligence (AGI).
iFADIT: Invertible Face Anonymization via Disentangled Identity Transform
However, many still face limitations in visual quality and often overlook the potential to recover the original face from the anonymized version, which can be valuable in specific contexts such as image forensics.
Online Video Understanding: OVBench and VideoChat-Online
Despite the lower computational cost and higher efficiency, VideoChat-Online outperforms existing state-of-the-art offline and online models across popular offline video benchmarks and OVBench, demonstrating the effectiveness of our model architecture and training strategy.
Do Current Video LLMs Have Strong OCR Abilities? A Preliminary Study
With the rise of multimodal large language models, accurately extracting and understanding textual information from video content, referred to as video based optical character recognition (Video OCR), has become a crucial capability.
VideoMaker: Zero-shot Customized Video Generation with the Inherent Force of Video Diffusion Models
Zero-shot customized video generation has gained significant attention due to its substantial application potential.
NoisyEQA: Benchmarking Embodied Question Answering Against Noisy Queries
Additionally, we also propose a 'Self-Correction' prompting mechanism and a new evaluation metric to enhance and measure both noise detection capability and answer quality.
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
In this paper, we propose to build efficient MLLMs by leveraging the Mixture-of-Depths (MoD) mechanism, where each transformer decoder layer selects essential vision tokens to process while skipping redundant ones.
CamI2V: Camera-Controlled Image-to-Video Diffusion Model
We innovatively associate the quality of a condition with its ability to reduce uncertainty and interpret noisy cross-frame features as a form of noisy condition.
GISExplainer: On Explainability of Graph Neural Networks via Game-theoretic Interaction Subgraphs
First, GISExplainer defines a causal attribution mechanism that considers the game-theoretic interaction of multi-granularity coalitions in candidate explanatory subgraph to quantify the causal effect of an edge on the prediction.
AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding
With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning.
Semantic Alignment for Multimodal Large Language Models
By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM.
CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities
In this paper, we propose CustomCrafter, a novel framework that preserves the model's motion generation and conceptual combination abilities without additional video and fine-tuning to recovery.
HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
In this paper, we introduce HAFormer, a model that combines the hierarchical features extraction ability of CNNs with the global dependency modeling capability of Transformers to tackle lightweight semantic segmentation challenges.
Explainable AI Security: Exploring Robustness of Graph Neural Networks to Adversarial Attacks
Graph neural networks (GNNs) have achieved tremendous success, but recent studies have shown that GNNs are vulnerable to adversarial attacks, which significantly hinders their use in safety-critical scenarios.
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning
Numerous adversarial defense methods on GNNs are proposed to address the problem of adversarial attacks.
Open-Vocabulary Spatio-Temporal Action Detection
Open-vocabulary spatio-temporal action detection (OV-STAD) requires training a model on a limited set of base classes with box and label supervision, which is expected to yield good generalization performance on novel action classes.
STMixer: A One-Stage Sparse Action Detector
First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain.
SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos
We hope that SportsHHI can stimulate research on human interaction understanding in videos and promote the development of spatio-temporal context modeling techniques in video visual relation detection.
SphereDiffusion: Spherical Geometry-Aware Distortion Resilient Diffusion Model
Controllable spherical panoramic image generation holds substantial applicative potential across a variety of domains. However, it remains a challenging task due to the inherent spherical distortion and geometry characteristics, resulting in low-quality content generation. In this paper, we introduce a novel framework of SphereDiffusion to address these unique challenges, for better generating high-quality and precisely controllable spherical panoramic images. For the spherical distortion characteristic, we embed the semantics of the distorted object with text encoding, then explicitly construct the relationship with text-object correspondence to better use the pre-trained knowledge of the planar images. Meanwhile, we employ a deformable technique to mitigate the semantic deviation in latent space caused by spherical distortion. For the spherical geometry characteristic, in virtue of spherical rotation invariance, we improve the data diversity and optimization objectives in the training process, enabling the model to better learn the spherical geometry characteristic. Furthermore, we enhance the denoising process of the diffusion model, enabling it to effectively use the learned geometric characteristic to ensure the boundary continuity of the generated images. With these specific techniques, experiments on Structured3D dataset show that SphereDiffusion significantly improves the quality of controllable spherical image generation and relatively reduces around 35% FID on average.
CR-SAM: Curvature Regularized Sharpness-Aware Minimization
However, as training progresses, the non-linearity of the loss landscape increases, rendering one-step gradient ascent less effective.
LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate
The transferability of adversarial examples is of central importance to transfer-based black-box adversarial attacks.
MFPNet: Multi-scale Feature Propagation Network For Lightweight Semantic Segmentation
In contrast to the abundant research focusing on large-scale models, the progress in lightweight semantic segmentation appears to be advancing at a comparatively slower pace.
PRO-Face S: Privacy-preserving Reversible Obfuscation of Face Images via Secure Flow
This paper proposes a novel paradigm for facial privacy protection that unifies multiple characteristics including anonymity, diversity, reversibility and security within a single lightweight framework.
GNP Attack: Transferable Adversarial Examples via Gradient Norm Penalty
Adversarial examples (AE) with good transferability enable practical black-box attacks on diverse target models, where insider knowledge about the target models is not required.
SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation
Experimental results on Stanford2D3D Panoramic datasets show that SGAT4PASS significantly improves performance and robustness, with approximately a 2% increase in mIoU, and when small 3D disturbances occur in the data, the stability of our performance is improved by an order of magnitude.
Ranked #4 on
Semantic Segmentation
on Stanford2D3D Panoramic
SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.
Generative Graph Neural Networks for Link Prediction
Instead of sampling positive and negative links and heuristically computing the features of their enclosing subgraphs, GraphLP utilizes the feature learning ability of deep-learning models to automatically extract the structural patterns of graphs for link prediction under the assumption that real-world graphs are not locally isolated.
FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information
To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion).
Learning Deep Representations via Contrastive Learning for Instance Retrieval
To begin with, we investigate the efficacy of transfer learning in IIR, by comparing off-the-shelf features learned by a pre-trained deep neural network (DNN) classifier with features learned by a CL model.
Interactive Image Synthesis with Panoptic Layout Generation
In particular, the stuff layouts can take amorphous shapes and fill up the missing regions left out by the instance layouts.
Ranked #2 on
Layout-to-Image Generation
on Visual Genome 128x128
Onsite Non-Line-of-Sight Imaging via Online Calibrations
There has been an increasing interest in deploying non-line-of-sight (NLOS) imaging systems for recovering objects behind an obstacle.
Self-adaptive Multi-task Particle Swarm Optimization
In the focus search strategy, if there is no knowledge source benefit the optimization of a task, then all knowledge sources in the task's pool are forbidden to be utilized except the task, which helps to improve the performance of the proposed algorithm.
Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding
Instead, from a perspective on temporal grounding as a metric-learning problem, we present a Mutual Matching Network (MMN), to directly model the similarity between language queries and video moments in a joint embedding space.
Ranked #3 on
Temporal Sentence Grounding
on Charades-STA
Fine-Grained Shape-Appearance Mutual Learning for Cloth-Changing Person Re-Identification
Recently, person re-identification (Re-ID) has achieved great progress.
Ranked #5 on
Person Re-Identification
on VC-Clothes
Microsoft Recommenders: Tools to Accelerate Developing Recommender Systems
The purpose of this work is to highlight the content of the Microsoft Recommenders repository and show how it can be used to reduce the time involved in developing recommender systems.
Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation.
Drosophila-Inspired 3D Moving Object Detection Based on Point Clouds
3D moving object detection is one of the most critical tasks in dynamic scene analysis.
Optimization of Graph Total Variation via Active-Set-based Combinatorial Reconditioning
Structured convex optimization on weighted graphs finds numerous applications in machine learning and computer vision.
Modeling Information Need of Users in Search Sessions
Users issue queries to Search Engines, and try to find the desired information in the results produced.
Informative GANs via Structured Regularization of Optimal Transport
We tackle the challenge of disentangled representation learning in generative adversarial networks (GANs) from the perspective of regularized optimal transport (OT).
Variational Uncalibrated Photometric Stereo under General Lighting
Photometric stereo (PS) techniques nowadays remain constrained to an ideal laboratory setup where modeling and calibration of lighting is amenable.
Optimization of Inf-Convolution Regularized Nonconvex Composite Problems
In this work, we consider nonconvex composite problems that involve inf-convolution with a Legendre function, which gives rise to an anisotropic generalization of the proximal mapping and Moreau-envelope.
Probabilistic Discriminative Learning with Layered Graphical Models
Probabilistic graphical models are traditionally known for their successes in generative modeling.
Detailed Dense Inference with Convolutional Neural Networks via Discrete Wavelet Transform
Dense pixelwise prediction such as semantic segmentation is an up-to-date challenge for deep convolutional neural networks (CNNs).
Network Reconstruction and Controlling Based on Structural Regularity Analysis
In addition, the model is capable of measuring the importance of microscopic network elements, i. e., nodes and links, in terms of network regularity thereby allowing us to regulate the reconstructability of networks based on them.
Combinatorial Preconditioners for Proximal Algorithms on Graphs
We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners.
LED-based Photometric Stereo: Modeling, Calibration and Numerical Solution
The second one directly recovers the depth, by formulating photometric stereo as a system of PDEs which are partially linearized using image ratios.
A Non-Convex Variational Approach to Photometric Stereo Under Inaccurate Lighting
This paper tackles the photometric stereo problem in the presence of inaccurate lighting, obtained either by calibration or by an uncalibrated photometric stereo method.
Retrospective Higher-Order Markov Processes for User Trails
In this paper we propose the retrospective higher-order Markov process (RHOMP) as a low-parameter model for such sequences.
General Tensor Spectral Co-clustering for Higher-Order Data
Spectral clustering and co-clustering are well-known techniques in data analysis, and recent work has extended spectral clustering to square, symmetric tensors and hypermatrices derived from a network.
Multi-way Monte Carlo Method for Linear Systems
A sufficient condition for the method to work is $\| H \| < 1$, which greatly limits the usability of this method.
Pure Price of Anarchy for Generalized Second Price Auction
Previous studies have shown that the pure Price Of Anarchy (POA) of GSP is 1. 25 when there are two ad slots and 1. 259 when three ad slots.
Computer Science and Game Theory
