Search Results for author:
Found 37 papers, 7 papers with code
LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods
Through extensive experiments, we reveal slight deviations (approximately 0. 2 Mandelbrot exponent) from Mandelbrot's law in LLMNL, underscore a complexity advantage in HNL, and supplement an interpretive discussion on language style.
Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
Our research provides a psychological explanation of the jailbreak prompts.
Exploring the Law of Numbers: Evidence from China's Real Estate
The renowned proverb, Numbers do not lie, underscores the reliability and insight that lie beneath numbers, a concept of undisputed importance, especially in economics and finance etc.
Will Sentiment Analysis Need Subculture? A New Data Augmentation Approach
The renowned proverb that "The pen is mightier than the sword" underscores the formidable influence wielded by text expressions in shaping sentiments.
Exploring the law of text geographic information
Textual geographic information is indispensable and heavily relied upon in practical applications.
Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models
Inspired by the attack that penetrates traditional firewalls through reverse tunnels, we introduce a "self-deception" attack that can bypass the semantic firewall by inducing LLM to generate prompts that facilitate jailbreak.
CTVIS: Consistent Training for Online Video Instance Segmentation
The discrimination of instance embeddings plays a vital role in associating instances across time for online video instance segmentation (VIS).
Ranked #3 on
Video Instance Segmentation
on Youtube-VIS 2022 Validation
(using extra training data)
Human-to-Human Interaction Detection
First, based on the popular AVA dataset created for action detection, we establish a new HID benchmark, termed AVA-Interaction (AVA-I), by adding annotations on interactive relations in a frame-by-frame manner.
3D Object Aided Self-Supervised Monocular Depth Estimation
Specifically, we first detect 3D objects in the images and build the per-pixel correspondence of the dynamic pixels with the detected object pose while leaving the static pixels corresponding to the rigid background to be modeled with camera motion.
A new hazard event classification model via deep learning and multifractal
Then, a new multifractal analysis method termed HmF-DFA is proposed to win HaE fractal series by analyzing HaE time series.
Yes, DLGM! A novel hierarchical model for hazard classification
In this paper, we propose a novel model termed DLGM via deep learning for hazard classification.
A Zipf's Law-based Text Generation Approach for Addressing Imbalance in Entity Extraction
The Zipf's Law emerges as a well-suited adoption, and to transition from words to entities, words within the documents are classified as common and rare ones.
CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation
LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms.
Ranked #12 on
Robust 3D Semantic Segmentation
on SemanticKITTI-C
ISDA: Position-Aware Instance Segmentation with Deformable Attention
Most instance segmentation models are not end-to-end trainable due to either the incorporation of proposal estimation (RPN) as a pre-processing or non-maximum suppression (NMS) as a post-processing.
Ranked #17 on
Instance Segmentation
on COCO test-dev
(APL metric)
A New Multifractal-based Deep Learning Model for Text Mining
In this world full of uncertainty, where the fabric of existence weaves patterns of complexity, multifractal emerges as beacons of insight, illuminating them.
Chinese Named Entity Recognition
named-entity-recognition
+1
A novel knowledge graph development for industry design: A case study on indirect coal liquefaction process
In order to reuse and unlock the value of ISK and optimize HAZOP, we have developed a novel knowledge graph for industrial safety (ISKG) with HAZOP as the carrier through bridging data science and engineering design.
Why KDAC? A general activation function for knowledge discovery
We hope that KDAC can be exploited as a promising activation function to devote itself to the construction of knowledge.
Are deep learning models superior for missing data imputation in large surveys? Evidence from an empirical comparison
We conduct extensive simulation studies based on a subsample of the American Community Survey to compare the repeated sampling properties of four machine learning based MI methods: MICE with classification trees, MICE with random forests, generative adversarial imputation networks, and multiple imputation using denoising autoencoders.
Operator means in JB-algebras
In this paper, the notion of operator means in the setting of JB-algebras is introduced and their properties are studied.
Functional Analysis Mathematical Physics Mathematical Physics 47A63, 47A64, 46H70, 47A60(Primary), 17C65, 81R15, 81P45, 94C99(Secondary)
Accurate Object Association and Pose Updating for Semantic SLAM
The key to solving this problem is to correctly associate multiple object measurements of one object landmark, and refine the pose of object landmark.
Graph Attention Tracking
We propose to establish part-to-part correspondence between the target and the search region with a complete bipartite graph, and apply the graph attention mechanism to propagate target information from the template feature to the search feature.
Consistency-Aware Graph Network for Human Interaction Understanding
Compared with the progress made on human activity classification, much less success has been achieved on human interaction understanding (HIU).
Optimal Equilibria for Multi-dimensional Time-inconsistent Stopping Problems
We study an optimal stopping problem under non-exponential discounting, where the state process is a multi-dimensional continuous strong Markov process.
SiamCAR: Siamese Fully Convolutional Classification and Regression for Visual Tracking
The proposed framework SiamCAR consists of two simple subnetworks: one Siamese subnetwork for feature extraction and one classification-regression subnetwork for bounding box prediction.
New Convex Relaxations for MRF Inference With Unknown Graphs
The CCCP algorithm is initialized by solving a convex QP relaxation of the problem, which is obtained by modifying the diagonal of the matrix that specifies the non-convex QP relaxation.
End-to-end feature fusion siamese network for adaptive visual tracking
Both features and the channel weights are utilized in a template generation layer to generate a discriminative template.
DCI: Discriminative and Contrast Invertible Descriptor
In this paper, we proposed a Discriminative and Contrast Invertible (DCI) local feature descriptor.
ALIGNet: Partial-Shape Agnostic Alignment via Unsupervised Learning
The process of aligning a pair of shapes is a fundamental operation in computer graphics.
Neuron-level Selective Context Aggregation for Scene Segmentation
Contextual information provides important cues for disambiguating visually similar pixels in scene segmentation.
Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks
In this paper, we tackle the problem of RGB-D semantic segmentation of indoor images.
Recurrent Attentional Networks for Saliency Detection
Convolutional-deconvolution networks can be adopted to perform end-to-end saliency detection.
Synthesizing Training Images for Boosting Human 3D Pose Estimation
Human 3D pose estimation from a single image is a challenging task with numerous applications.
Recent Advances in Convolutional Neural Networks
In the last few years, deep learning has led to very good performance on a variety of problems, such as visual recognition, speech recognition and natural language processing.
Learning Fine-grained Features via a CNN Tree for Large-scale Classification
The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by learning features only among these classes.
Affine Subspace Representation for Feature Description
This paper proposes a novel Affine Subspace Representation (ASR) descriptor to deal with affine distortions induced by viewpoint changes.
A Hybrid Loss for Multiclass and Structured Prediction
We propose a novel hybrid loss for multiclass and structured prediction problems that is a convex combination of a log loss for Conditional Random Fields (CRFs) and a multiclass hinge loss for Support Vector Machines (SVMs).
Bilinear Programming for Human Activity Recognition with Unknown MRF Graphs
Markov Random Fields (MRFs) have been successfully applied to human activity modelling, largely due to their ability to model complex dependencies and deal with local uncertainty.
