Search Results for author:
Found 41 papers, 20 papers with code
Weakly Supervised Deep Hyperspherical Quantization for Image Retrieval
Deep quantization methods have shown high efficiency on large-scale image retrieval.
RAT: Retrieval-Augmented Transformer for Click-Through Rate Prediction
Predicting click-through rates (CTR) is a fundamental task for Web applications, where a key issue is to devise effective models for feature interactions.
Sequence-level Semantic Representation Fusion for Recommender Systems
The core idea of our approach is to conduct a sequence-level semantic fusion approach by better integrating global contexts.
Prompting Large Language Models for Recommender Systems: A Comprehensive Framework and Empirical Analysis
As for the use of LLMs as recommenders, we analyze the impact of public availability, tuning strategies, model architecture, parameter scale, and context length on recommendation results based on the classification of LLMs.
Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition
Illumination variation has been a long-term challenge in real-world facial expression recognition(FER).
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition
With the strong robusticity on illumination variations, near-infrared (NIR) can be an effective and essential complement to visible (VIS) facial expression recognition in low lighting or complete darkness conditions.
Facial Expression Recognition
Facial Expression Recognition (FER)
Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compression
In this paper, we propose a progressive learning paradigm for transformer-based variable-rate image compression.
What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning
By conducting a comprehensive empirical study, we find that instructions focused on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs on evaluation benchmarks.
GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video Retrieval
Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead.
PREFER: Prompt Ensemble Learning via Feedback-Reflect-Refine
Moreover, to enhance stability of the prompt effect evaluation, we propose a novel prompt bagging method involving forward and backward thinking, which is superior to majority voting and is beneficial for both feedback and weight calculation in boosting.
MISSRec: Pre-training and Transferring Multi-modal Interest-aware Sequence Representation for Recommendation
We propose MISSRec, a multi-modal pre-training and transfer learning framework for SR. On the user side, we design a Transformer-based encoder-decoder model, where the contextual encoder learns to capture the sequence-level multi-modal user interests while a novel interest-aware decoder is developed to grasp item-modality-interest relations for better sequence representation.
Evaluating Object Hallucination in Large Vision-Language Models
Despite the promising progress on LVLMs, we find that LVLMs suffer from the hallucination problem, i. e. they tend to generate objects that are inconsistent with the target images in the descriptions.
Keyword-Based Diverse Image Retrieval by Semantics-aware Contrastive Learning and Transformer
On the one hand, standard retrieval systems are usually biased to common semantics and seldom exploit diversity-aware regularization in training, which makes it difficult to promote diversity by post-processing.
Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models
To conquer this limitation, we propose a novel Instance-aware Dynamic Prompt Tuning (IDPT) strategy for pre-trained point cloud models.
Contrastive Masked Autoencoders for Self-Supervised Video Hashing
To capture video semantic information for better hashing learning, we adopt an encoder-decoder structure to reconstruct the video from its temporal-masked frames.
Hybrid Contrastive Quantization for Efficient Cross-View Video Retrieval
By performing Asymmetric-Quantized Contrastive Learning (AQ-CL) across views, HCQ aligns texts and videos at coarse-grained and multiple fine-grained levels.
Suppressing Static Visual Cues via Normalizing Flows for Self-Supervised Video Representation Learning
By modelling static factors in a video as a random variable, the conditional distribution of each latent variable becomes shifted and scaled normal.
Cross-Batch Negative Sampling for Training Two-Tower Recommenders
The two-tower architecture has been widely applied for learning item and user representations, which is important for large-scale recommender systems.
SimpleX: A Simple and Strong Baseline for Collaborative Filtering
While many existing studies focus on the design of more powerful interaction encoders, the impacts of loss functions and negative sampling ratios have not yet been well explored.
Ranked #3 on
Recommendation Systems
on Yelp2018
Contrastive Quantization with Code Memory for Unsupervised Image Retrieval
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems.
PHPQ: Pyramid Hybrid Pooling Quantization for Efficient Fine-Grained Image Retrieval
To improve fine-grained image hashing, we propose Pyramid Hybrid Pooling Quantization (PHPQ).
ST-PIL: Spatial-Temporal Periodic Interest Learning for Next Point-of-Interest Recommendation
Specifically, in the long-term module, we learn the temporal periodic interest of daily granularity, then utilize intra-level attention to form long-term interest.
CANVASEMB: Learning Layout Representation with Large-scale Pre-training for Graphic Design
Layout representation, which models visual elements in a canvas and their inter-relations, plays a crucial role in graphic design intelligence.
Learning Semantic Correspondences from Noisy Data-text Pairs by Local-to-Global Alignments
Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input.
Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
Specifically, we construct a positive clip and a negative clip for each video.
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes.
Self-supervised Temporal Discriminative Learning for Video Representation Learning
Without labelled data for network pretraining, temporal triplet is generated for each anchor video by using segment of the same or different time interval so as to enhance the capacity for temporal feature representation.
Self-supervised learning using consistency regularization of spatio-temporal data augmentation for action recognition
Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data.
Improving Entity Linking by Modeling Latent Entity Type Information
Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility.
Ranked #2 on
Entity Disambiguation
on AIDA-CoNLL
(Micro-F1 metric)
Enhancing Neural Data-To-Text Generation Models with External Background Knowledge
Recent neural models for data-to-text generation rely on massive parallel pairs of data and text to learn the writing knowledge.
An Encoder with non-Sequential Dependency for Neural Data-to-Text Generation
Data-to-text generation aims to generate descriptions given a structured input data (i. e., a table with multiple records).
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation
Recent neural language generation systems often \textit{hallucinate} contents (i. e., producing irrelevant or contradicted facts), especially when trained on loosely corresponding pairs of the input structure and text.
Data2Text Studio: Automated Text Generation from Structured Data
Data2Text Studio is a platform for automated text generation from structured data.
Operation-guided Neural Networks for High Fidelity Data-To-Text Generation
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
Aggregated Semantic Matching for Short Text Entity Linking
The task of entity linking aims to identify concepts mentioned in a text fragments and link them to a reference knowledge base.
Learning Latent Semantic Annotations for Grounding Natural Language to Structured Data
Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms.
Operations Guided Neural Networks for High Fidelity Data-To-Text Generation
Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.
Incorporating Consistency Verification into Neural Data-to-Document Generation
Recent neural models for data-to-document generation have achieved remarkable progress in producing fluent and informative texts.
A Statistical Framework for Product Description Generation
We present in this paper a statistical framework that generates accurate and fluent product description from product attributes.
