Search Results for author:
Found 44 papers, 15 papers with code
Towards Scalability and Extensibility of Query Reformulation Modeling in E-commerce Search
Notably, employing the proposed solution in search ranking resulted in 0. 14% and 0. 29% increase in overall revenue in Japanese and Hindi cases, respectively, and a 0. 08\% incremental gain in the English case compared to the legacy implementation; while in search Ads matching led to a 0. 36% increase in Ads revenue in the Japanese case.
Context-Former: Stitching via Latent Conditioned Sequence Modeling
On the other hand, Decision Transformer (DT) abstracts the decision-making as sequence modeling, showcasing competitive performance on offline RL benchmarks, however, recent studies demonstrate that DT lacks of stitching capability, thus exploit stitching capability for DT is vital to further improve its performance.
NFT1000: A Visual Text Dataset For Non-Fungible Token Retrieval
With the rise of 'Metaverse' and 'Web3. 0', NFT ( Non-Fungible Token ) has emerged as a kind of pivotal digital asset, garnering significant attention.
Set Prediction Guided by Semantic Concepts for Diverse Video Captioning
Each caption in the set is attached to a concept combination indicating the primary semantic content of the caption and facilitating element alignment in set prediction.
A dynamical clipping approach with task feedback for Proximal Policy Optimization
Different from previous clipping approaches, we consider increasing the maximum cumulative Return in reinforcement learning (RL) tasks as the preference of the RL task, and propose a bi-level proximal policy optimization paradigm, which involves not only optimizing the policy but also dynamically adjusting the clipping bound to reflect the preference of the RL tasks to further elevate the training outcomes and stability of PPO.
No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML
These solutions, referred to as TEE-Shielded DNN Partition (TSDP), partition a DNN model into two parts, offloading the privacy-insensitive part to the GPU while shielding the privacy-sensitive part within the TEE.
Sample Efficient Reward Augmentation in offline-to-online Reinforcement Learning
Offline-to-online RL can make full use of pre-collected offline datasets to initialize policies, resulting in higher sample efficiency and better performance compared to only using online algorithms alone for policy training.
Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning
Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data.
The Barriers to Online Clothing Websites for Visually Impaired People: An Interview and Observation Approach to Understanding Needs
Visually impaired (VI) people often face challenges when performing everyday tasks and identify shopping for clothes as one of the most challenging.
Mining Healthcare Procurement Data Using Text Mining and Natural Language Processing -- Reflection From An Industrial Project
In this work, we describe an industry project that developed text mining and NLP solutions to mine millions of heterogeneous, multilingual procurement documents in the healthcare sector.
ViLEM: Visual-Language Error Modeling for Image-Text Retrieval
ViLEM then enforces the model to discriminate the correctness of each word in the plausible negative texts and further correct the wrong words via resorting to image information.
Ranked #45 on
Visual Reasoning
on Winoground
Order-Prompted Tag Sequence Generation for Video Tagging
This paper proposes a novel generative model, Order-Prompted Tag Sequence Generation (OP-TSG), according to the above characteristics.
Decoupled Mixup for Generalized Visual Recognition
Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair.
Can Offline Reinforcement Learning Help Natural Language Understanding?
Experimental results show that our RL pre-trained models can give close performance compared with the models using the LM training objective, showing that there exist common useful features across these two modalities.
KSG: Knowledge and Skill Graph
This is the first study that we are aware of that looks into dynamic KSG for skill retrieval and learning.
A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
The results illustrate that there is a utility-privacy tradeoff for sharing synthetic EHR data.
PIC 4th Challenge: Semantic-Assisted Multi-Feature Encoding and Multi-Head Decoding for Dense Video Captioning
The task of Dense Video Captioning (DVC) aims to generate captions with timestamps for multiple events in one video.
Distillation to Enhance the Portability of Risk Models Across Institutions with Large Patient Claims Database
We further show that the transfer learning approach based on the BAN produces models that are better than those trained on just a single institution's data.
CREATE: A Benchmark for Chinese Short Video Retrieval and Title Generation
In this paper, we propose to CREATE, the first large-scale Chinese shoRt vidEo retrievAl and Title gEneration benchmark, to facilitate research and application in video titling and video retrieval in Chinese.
DistFL: Distribution-aware Federated Learning for Mobile Scenarios
Previous studies focus on the "symptoms" directly, as they try to improve the accuracy or detect possible attacks by adding extra steps to conventional FL models.
Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value than the easy cases.
Text-Driven Image Manipulation via Semantic-Aware Knowledge Transfer
And on this basis, a novel attribute transfer method, named semantic directional decomposition network (SDD-Net), is proposed to achieve semantic-level facial attribute transfer by latent semantic direction decomposition, improving the interpretability and editability of our method.
SS-BERT: Mitigating Identity Terms Bias in Toxic Comment Classification by Utilising the Notion of "Subjectivity" and "Identity Terms"
Toxic comment classification models are often found biased toward identity terms which are terms characterizing a specific group of people such as "Muslim" and "black".
An Exploratory Study on Utilising the Web of Linked Data for Product Data Mining
We process billions of structured data points in the form of RDF n-quads, to create multi-million words of product-related corpora that are later used in three different ways for creating of language resources: training word embedding models, continued pre-training of BERT-like language models, and training Machine Translation models that are used as a proxy to generate product-related keywords.
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
Graph convolutional networks (GCNs) have been widely used and achieved remarkable results in skeleton-based action recognition.
Ranked #9 on
Skeleton Based Action Recognition
on N-UCLA
ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
The knowledge of a deep learning model may be transferred to a student model, leading to intellectual property infringement or vulnerability propagation.
PDNet: Toward Better One-Stage Object Detection With Prediction Decoupling
However, the most suitable positions for inferring different targets, i. e., the object category and boundaries, are generally different.
Blending Knowledge in Deep Recurrent Networks for Adverse Event Prediction at Hospital Discharge
Deep learning architectures have an extremely high-capacity for modeling complex data in a wide variety of domains.
Open-book Video Captioning with Retrieve-Copy-Generate Network
Due to the rapid emergence of short videos and the requirement for content understanding and creation, the video captioning task has received increasing attention in recent years.
Depth Self-Optimized Learning Toward Data Science
We propose a two-stage model called Depth Self-Optimized Learning (DSOL), which aims to realize ANN depth self-configuration, self-optimization as well as ANN training without manual intervention.
Backdoor Attack against Speaker Verification
We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
Open-sourced Dataset Protection via Backdoor Watermarking
Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples ($i. e.$, images with trigger) on the target class.
Understanding and Diagnosing Vulnerability under Adversarial Attacks
Moreover, we design the first diagnostic method to quantify the vulnerability contributed by each layer, which can be used to identify vulnerable parts of model architectures.
Adversarial Attacks on Monocular Depth Estimation
In order to understand the impact of adversarial attacks on depth estimation, we first define a taxonomy of different attack scenarios for depth estimation, including non-targeted attacks, targeted attacks and universal attacks.
Generating Electronic Health Records with Multiple Data Types and Constraints
Sharing electronic health records (EHRs) on a large scale may lead to privacy intrusions.
Object Relational Graph with Teacher-Recommended Learning for Video Captioning
In this paper, we propose a complete video captioning system including both a novel model and an effective training strategy.
Ranked #9 on
Video Captioning
on VATEX
(using extra training data)
Efficient Adversarial Training with Transferable Adversarial Examples
Adversarial training is an effective defense method to protect classification models against adversarial attacks.
VATEX Captioning Challenge 2019: Multi-modal Information Fusion and Multi-stage Training Strategy for Video Captioning
Multi-modal information is essential to describe what has happened in a video.
Fashion Editing with Adversarial Parsing Learning
Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value.
Hate Speech Detection: A Solved Problem? The Challenging Case of Long Tail on Twitter
Our methods are evaluated on the largest collection of hate speech datasets based on Twitter, and are shown to be able to outperform the best performing method by up to 5 percentage points in macro-average F1, or 8 percentage points in the more challenging case of identifying hateful content.
SemRe-Rank: Improving Automatic Term Extraction By Incorporating Semantic Relatedness With Personalised PageRank
Extensively evaluated with 13 state-of-the-art base ATE methods on four datasets of diverse nature, it is shown to have achieved widespread improvement over all base methods and across all datasets, with up to 15 percentage points when measured by the Precision in the top ranked K candidate terms (the average for a set of K's), or up to 28 percentage points in F1 measured at a K that equals to the expected real terms in the candidates (F1 in short).
JATE 2.0: Java Automatic Term Extraction with Apache Solr
Automatic Term Extraction (ATE) or Recognition (ATR) is a fundamental processing step preceding many complex knowledge engineering tasks.
Automatically Extracting Procedural Knowledge from Instructional Texts using Natural Language Processing
Procedural knowledge is the knowledge required to perform certain tasks, and forms an important part of expertise.
