Search Results for author:
Found 30 papers, 15 papers with code
Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction
As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews.
Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
To address this challenge, we introduce Conifer, a novel instruction tuning dataset, designed to enhance LLMs to follow multi-level instructions with complex constraints.
EL-VIT: Probing Vision Transformer with Interactive Visualization
Therefore, a visualization system is needed to assist ViT users in understanding its functionality.
Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach
It comprises two core components: a snippet clustering component that groups the snippets into multiple latent clusters and a cluster classification component that further classifies the cluster as foreground or background.
SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention
Zero-shot voice conversion (VC) aims to transfer the source speaker timbre to arbitrary unseen target speaker timbre, while keeping the linguistic content unchanged.
GAIA: Delving into Gradient-based Attribution Abnormality for Out-of-distribution Detection
This perspective is motivated by our observation that gradient-based attribution methods encounter challenges in assigning feature importance to OOD data, thereby yielding divergent explanation patterns.
Generalizable Person Search on Open-world User-Generated Video Content
Person search is a challenging task that involves detecting and retrieving individuals from a large set of un-cropped scene images.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
Detecting Out-of-distribution Examples via Class-conditional Impressions Reappearing
Out-of-distribution (OOD) detection aims at enhancing standard deep neural networks to distinguish anomalous inputs from original training data.
Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search
Text-based Person Search (TPS), is targeted on retrieving pedestrians to match text descriptions instead of query images.
Video Semantic Segmentation with Inter-Frame Feature Fusion and Inner-Frame Feature Refinement
In this paper, to tackle the misalignment issue, we propose a spatial-temporal fusion (STF) module to model dense pairwise relationships among multi-frame features.
Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo-labels, while ignoring the importance of training the segmentation networks.
Towards Effective Instance Discrimination Contrastive Loss for Unsupervised Domain Adaptation
We further propose a target-dominated cross-domain mixup that can incorporate accurate semantic information from the source domain.
Efficient Cavity Searching for Gene Network of Influenza A Virus
High order structures (cavities and cliques) of the gene network of influenza A virus reveal tight associations among viruses during evolution and are key signals that indicate viral cross-species infection and cause pandemics.
VCSE: Time-Domain Visual-Contextual Speaker Extraction Network
In the first stage, we pre-extract a target speech with visual cues and estimate the underlying phonetic sequence.
SoccerNet 2022 Challenges Results
The SoccerNet 2022 challenges were the second annual video understanding challenges organized by the SoccerNet team.
Exploring High-quality Target Domain Information for Unsupervised Domain Adaptive Semantic Segmentation
Such a strategy can generate the object boundaries in target domain (edge of target-domain object areas) with the correct labels.
Domain Adaptive Person Search
In this paper, we take a further step and present Domain Adaptive Person Search (DAPS), which aims to generalize the model from a labeled source domain to the unlabeled target domain.
Research on Dual Channel News Headline Classification Based on ERNIE Pre-training Model
Aiming at the problem that the traditional neural network model cannot adequately capture the underlying feature information of the data and cannot jointly extract key global features and deep local features, a dual-channel network model DC-EBAD based on the ERNIE pre-training model is proposed.
Low-confidence Samples Matter for Domain Adaptation
Representing the target data structure in such a way would overlook the huge low-confidence samples, resulting in sub-optimal transferability that is biased towards the samples similar to the source domain.
5th Place Solution for VSPW 2021 Challenge
In this article, we introduce the solution we used in the VSPW 2021 Challenge.
TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification
In the meantime, we design an adaptive BN layer in the domain-invariant stream, to approximate the statistics of various unseen domains.
Domain Generalization
Generalizable Person Re-identification
+1
Probabilistic Contrastive Learning for Domain Adaptation
However, it is undesirably observed that the standard contrastive paradigm (features+$\ell_{2}$ normalization) only brings little help for domain adaptation.
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check
Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters.
Ranked #1 on
Chinese Spell Checking
on SIGHAN 2015
IE-GAN: An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover Operator
The training of generative adversarial networks (GANs) is usually vulnerable to mode collapse and vanishing gradients.
Evolutionary Generative Adversarial Networks with Crossover Based Knowledge Distillation
Generative Adversarial Networks (GAN) is an adversarial model, and it has been demonstrated to be effective for various generative tasks.
Suphx: Mastering Mahjong with Deep Reinforcement Learning
Artificial Intelligence (AI) has achieved great success in many domains, and game AI is widely regarded as its beachhead since the dawn of AI.
Information Bottleneck Theory on Convolutional Neural Networks
Recent years, many researches attempt to open the black box of deep neural networks and propose a various of theories to understand it.
Attribute-aware Sequence Network for Review Summarization
Review summarization aims to generate a condensed summary for a review or multiple reviews.
Document-level Multi-aspect Sentiment Classification by Jointly Modeling Users, Aspects, and Overall Ratings
The document representation is combined with user and overall rating information to predict aspect ratings of a review.
