Search Results for author:
Found 68 papers, 27 papers with code
De-Biased Court's View Generation with Causality
Court{'}s view generation is a novel but essential task for legal AI, aiming at improving the interpretability of judgment prediction results and enabling automatic legal document generation.
ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis
The task aims to extract the structured sentiment information (e. g., holder, target, expression and sentiment polarity) in a text.
Decomposed Prototype Learning for Few-Shot Scene Graph Generation
To this end, we propose a novel Decomposed Prototype Learning (DPL).
Learning Combinatorial Prompts for Universal Controllable Image Captioning
Due to its simplicity, our ComPro can easily be extended to more complex combined control signals by concatenating these prompts.
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Without bells and whistles, our RePro achieves a new state-of-the-art performance on two VidVRD benchmarks of not only the base training object and predicate categories, but also the unseen ones.
Further Improving Weakly-supervised Object Localization via Causal Knowledge Distillation
Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels.
Knowledge Distillation
Weakly-Supervised Object Localization
SAViT: Structure-Aware Vision Transformer Pruning via Collaborative Optimization
In this paper, we introduce joint importance, which integrates essential structural-aware interactions between components for the first time, to perform collaborative pruning.
DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis
To mine the information in probability volume, we creatively synthesize the source depths by splattering the probability volume and depth hypotheses to source views.
Label Semantic Knowledge Distillation for Unbiased Scene Graph Generation
To this end, we propose a novel model-agnostic Label Semantic Knowledge Distillation (LS-KD) for unbiased SGG.
Multi-scale Sampling and Aggregation Network For High Dynamic Range Imaging
High dynamic range (HDR) imaging is a fundamental problem in image processing, which aims to generate well-exposed images, even in the presence of varying illumination in the scenes.
Online Video Super-Resolution with Convolutional Kernel Bypass Graft
Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with ``kernel grafts'', which are extra convolutional kernels containing the prior knowledge of external pretrained image SR models.
Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation
However, we argue that most existing WSSGG works only focus on object-consistency, which means the grounded regions should have the same object category label as text entities.
Rethinking the Evaluation of Unbiased Scene Graph Generation
Current Scene Graph Generation (SGG) methods tend to predict frequent predicate categories and fail to recognize rare ones due to the severe imbalanced distribution of predicates.
Unified Normalization for Accelerating and Stabilizing Transformers
To tackle these issues, we propose Unified Normalization (UN), which can speed up the inference by being fused with other linear operations and achieve comparable performance on par with LN.
NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation
To this end, we propose a novel NoIsy label CorrEction and Sample Training strategy for SGG: NICEST.
Rethinking the Reference-based Distinctive Image Captioning
Unfortunately, reference images used by existing Ref-DIC works are easy to distinguish: these reference images only resemble the target image at scene-level and have few common objects, such that a Ref-DIC model can trivially generate distinctive captions even without considering the reference images.
Explicit Image Caption Editing
Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption.
Rethinking Data Augmentation for Robust Visual Question Answering
Unfortunately, to guarantee augmented samples have reasonable ground-truth answers, they manually design a set of heuristic rules for several question types, which extremely limits its generalization abilities.
Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging
Reconstructing ghosting-free high dynamic range (HDR) images of dynamic scenes from a set of multi-exposure images is a challenging task, especially with large object motion and occlusions, leading to visible artifacts using existing methods.
The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation
Then, in Pos-NSD, we use a clustering-based algorithm to divide all positive samples into multiple sets, and treat the samples in the noisiest set as noisy positive samples.
A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis
Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer.
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
From the view of feature, we break down the video into trajectories and first leverage trajectory feature in VideoQA to enhance the alignment between two modalities.
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them.
Ranked #11 on
Domain Adaptation
on GTA5 to Cityscapes
DepthGAN: GAN-based Depth Generation of Indoor Scenes from Semantic Layouts
Limited by the computational efficiency and accuracy, generating complex 3D scenes remains a challenging problem for existing generation networks.
Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
To deploy SSDR-AL in a more practical scenario, we design a noise-aware iterative labeling strategy to confront the "noisy annotation" problem introduced by the previous "dominant labeling" strategy in superpoints.
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation
Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years.
Ranked #5 on
Depth Estimation
on Stanford2D3D Panoramic
Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs
To this end, we propose a new classification-then-grounding framework for VidSGG, which can avoid all the three overlooked drawbacks.
Relational Graph Learning for Grounded Video Description Generation
Such a setting can help explain the decisions of captioning models and prevents the model from hallucinating object words in its description.
Consensus Graph Representation Learning for Better Grounded Image Captioning
The contemporary visual captioning models frequently hallucinate objects that are not actually in a scene, due to the visual misclassification or over-reliance on priors that resulting in the semantic inconsistency between the visual information and the target lexical words.
Unified Group Fairness on Federated Learning
We validate the advantages of the FMDA-M algorithm with various kinds of distribution shift settings in experiments, and the results show that FMDA-M algorithm outperforms the existing fair FL algorithms on unified group fairness.
Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering
Specifically, CSST is composed of two parts: Counterfactual Samples Synthesizing (CSS) and Counterfactual Samples Training (CST).
Natural Language Video Localization with Learnable Moment Proposals
Given an untrimmed video and a natural language query, Natural Language Video Localization (NLVL) aims to identify the video moment described by the query.
Instance-wise or Class-wise? A Tale of Neighbor Shapley for Concept-based Explanation
Deep neural networks have demonstrated remarkable performance in many data-driven and prediction-oriented applications, and sometimes even perform better than humans.
Video Relation Detection via Tracklet based Visual Transformer
Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years.
Progressive and Selective Fusion Network for High Dynamic Range Imaging
We propose a novel method that can better fuse the features based on two ideas.
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning
Specifically, Shapley Value and its desired properties are leveraged in deep MARL to credit any combinations of agents, which grants us the capability to estimate the individual credit for each agent.
Multi-agent Reinforcement Learning
reinforcement-learning
+3
Deep Learning for Weakly-Supervised Object Detection and Object Localization: A Survey
With the success of deep neural networks in object detection, both WSOD and WSOL have received unprecedented attention.
VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching
In this paper, we argue that these methods overlook an obvious \emph{mismatch} between the roles of proposals in the two stages: they generate proposals solely based on the detection confidence (i. e., query-agnostic), hoping that the proposals contain all instances mentioned in the text query (i. e., query-aware).
Improving Weakly-supervised Object Localization via Causal Intervention
The recent emerged weakly supervised object localization (WSOL) methods can learn to localize an object in the image only using image-level labels.
Efficient Ring-topology Decentralized Federated Learning with Deep Generative Models for Industrial Artificial Intelligent
A novel ring FL topology as well as a map-reduce based synchronizing method are designed in the proposed RDFL to improve decentralized FL performance and bandwidth utilization.
Human-like Controllable Image Captioning with Verb-specific Semantic Roles
However, we argue that almost all existing objective control signals have overlooked two indispensable characteristics of an ideal control signal: 1) Event-compatible: all visual contents referred to in a single sentence should be compatible with the described activity.
Boundary Proposal Network for Two-Stage Natural Language Video Localization
State-of-the-art NLVL methods are almost in one-stage fashion, which can be typically grouped into two categories: 1) anchor-based approach: it first pre-defines a series of video segment candidates (e. g., by sliding window), and then does classification for each candidate; 2) anchor-free approach: it directly predicts the probabilities for each video frame as a boundary or intermediate frame inside the positive segment.
Kinetic Energy Distribution of Fragments for Thermal Neutron-Induced $^{235}$U and $^{239}$Pu Fission Reactions
(2) Every complementary pair of the primary fission fragments is approximatively described as two ellipsoids with large deformation at scission moment.
Nuclear Theory
ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries
This work proposes a generic evaluation metric ROBY, a novel attack-independent robustness measure based on the model's decision boundaries.
GFL: A Decentralized Federated Learning Framework Based On Blockchain
Federated learning(FL) is a rapidly growing field and many centralized and decentralized FL frameworks have been proposed.
Federated Unsupervised Representation Learning
FURL poses two new challenges: (1) data distribution shift (Non-IID distribution) among clients would make local models focus on different categories, leading to the inconsistency of representation spaces.
Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding
The prevailing framework for solving referring expression grounding is based on a two-stage process: 1) detecting proposals with an object detector and 2) grounding the referent to one of the proposals.
Topic Adaptation and Prototype Encoding for Few-Shot Visual Storytelling
In this paper, we focus on enhancing the generalization ability of the VIST model by considering the few-shot setting.
Accurate Lung Nodules Segmentation with Detailed Representation Transfer and Soft Mask Supervision
Then, a novel Network with detailed representation transfer and Soft Mask supervision (DSNet) is proposed to process the input low-resolution images of lung nodules into high-quality segmentation results.
Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing
Multi-task learning is an effective learning strategy for deep-learning-based facial expression recognition tasks.
Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
Fashion outfit recommendation has attracted increasing attentions from online shopping services and fashion communities. Distinct from other scenarios (e. g., social networking or content sharing) which recommend a single item (e. g., a friend or picture) to a user, outfit recommendation predicts user preference on a set of well-matched fashion items. Hence, performing high-quality personalized outfit recommendation should satisfy two requirements -- 1) the nice compatibility of fashion items and 2) the consistence with user preference.
Counterfactual Samples Synthesizing for Robust Visual Question Answering
To reduce the language biases, several recent works introduce an auxiliary question-only model to regularize the training of targeted VQA model, and achieve dominating performance on VQA-CP.
Ranked #1 on
Visual Question Answering (VQA)
on VQA-CP
(using extra training data)
Evaluation Framework For Large-scale Federated Learning
Federated learning is proposed as a machine learning setting to enable distributed edge devices, such as mobile phones, to collaboratively learn a shared prediction model while keeping all the training data on device, which can not only take full advantage of data distributed across millions of nodes to train a good model but also protect data privacy.
Reinforcement-Learning based Portfolio Management with Augmented Asset Movement Prediction States
Our framework aims to address two unique challenges in financial PM: (1) data heterogeneity -- the collected information for each asset is usually diverse, noisy and imbalanced (e. g., news articles); and (2) environment uncertainty -- the financial market is versatile and non-stationary.
Video Dialog via Progressive Inference and Cross-Transformer
Video dialog is a new and challenging task, which requires the agent to answer questions combining video information with dialog history.
DEBUG: A Dense Bottom-Up Grounding Approach for Natural Language Video Localization
In this paper, we focus on natural language video localization: localizing (ie, grounding) a natural language description in a long and untrimmed video sequence.
Weak Supervision Enhanced Generative Network for Question Generation
More specifically, we devise a discriminator, Relation Guider, to capture the relations between the whole passage and the associated answer and then the Multi-Interaction mechanism is deployed to transfer the knowledge dynamically for our question generation system.
Galaxy Learning -- A Position Paper
Model training, as well as the communication, is achieved with blockchain and its smart contracts.
Counterfactual Critic Multi-Agent Training for Scene Graph Generation
CMAT is a multi-agent policy gradient method that frames objects as cooperative agents, and then directly maximizes a graph-level metric as the reward.
CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation with only image-level labels saves large human effort to annotate pixel-level labels.
Weakly supervised segmentation
Weakly supervised Semantic Segmentation
+1
Textually Guided Ranking Network for Attentional Image Retweet Modeling
In this paper, we study the problem of image retweet prediction in social media, which predicts the image sharing behavior that the user reposts the image tweets from their followees.
Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks
We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training.
Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks
Factorization Machines (FMs) are a supervised learning approach that enhances the linear regression model by incorporating the second-order feature interactions.
Graph-Theoretic Spatiotemporal Context Modeling for Video Saliency Detection
As a result, a key issue in video saliency detection is how to effectively capture the intrinsical properties of atomic video structures as well as their associated contextual interactions along the spatial and temporal dimensions.
Video Question Answering via Attribute-Augmented Attention Network Learning
Video Question Answering is a challenging problem in visual information retrieval, which provides the answer to the referenced video content according to the question.
On Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks
RNN-based approaches have achieved outstanding performance on action recognition with skeleton inputs.
Ranked #1 on
Skeleton Based Action Recognition
on SBU
SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
Existing visual attention models are generally spatial, i. e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image.
Metric Learning Driven Multi-Task Structured Output Optimization for Robust Keypoint Tracking
As an important and challenging problem in computer vision and graphics, keypoint-based object tracking is typically formulated in a spatio-temporal statistical learning framework.
