Search Results for author:
Found 125 papers, 56 papers with code
Text Speaks Louder than Vision: ASCII Art Reveals Textual Biases in Vision-Language Models
Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals across modalities remains underexplored.
MIRAGE: Multimodal Immersive Reasoning and Guided Exploration for Red-Team Jailbreak Attacks
While safety mechanisms have significantly progressed in filtering harmful text inputs, MLLMs remain vulnerable to multimodal jailbreaks that exploit their cross-modal reasoning capabilities.
SCORE: Soft Label Compression-Centric Dataset Condensation via Coding Rate Optimization
We argue that the three key properties to alleviate this performance-storage dilemma are informativeness, discriminativeness, and compressibility of the condensed data.
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization
However, we identify a critical limitation: not every adversarial optimization step leads to a positive outcome, and indiscriminately accepting optimization results at each step may reduce the overall attack success rate.
StableFusion: Continual Video Retrieval via Frame Adaptation
Text-to-Video Retrieval (TVR) aims to match videos with corresponding textual queries, yet the continual influx of new video content poses a significant challenge for maintaining system performance over time.
SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize unseen classes without labeled training examples by leveraging class-level semantic descriptors such as attributes.
TT-GaussOcc: Test-Time Compute for Self-Supervised Occupancy Prediction via Spatio-Temporal Gaussian Splatting
Self-supervised 3D occupancy prediction offers a promising solution for understanding complex driving scenes without requiring costly 3D annotations.
MAA: Meticulous Adversarial Attack against Vision-Language Pre-trained Models
Current adversarial attacks for evaluating the robustness of vision-language pre-trained (VLP) models in multi-modal tasks suffer from limited transferability, where attacks crafted for a specific model often struggle to generalize effectively across different models, limiting their utility in assessing robustness more broadly.
GOLD: Graph Out-of-Distribution Detection via Implicit Adversarial Latent Generation
The implicit adversarial training process employs a novel alternating optimisation framework by training: (1) a latent generative model to regularly imitate the in-distribution (ID) embeddings from an evolving GNN, and (2) a GNN encoder and an OOD detector to accurately classify ID data while increasing the energy divergence between the ID embeddings and the generative model's synthetic embeddings.
Lost in Edits? A $λ$-Compass for AIGC Provenance
Recent advancements in diffusion models have driven the growth of text-guided image editing tools, enabling precise and iterative modifications of synthesized content.
Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
Pre-training vision-language representations on human action videos has emerged as a promising approach to reduce reliance on large-scale expert demonstrations for training embodied agents.
Radar Signal Recognition through Self-Supervised Learning and Domain Adaptation
Specifically, we investigate pre-training masked autoencoders (MAE) on baseband in-phase and quadrature (I/Q) signals from various RF domains and subsequently transfer the learned representation to the radar domain, where annotated data are limited.
RadDet: A Wideband Dataset for Real-Time Radar Spectrum Detection
To address this challenge, we introduce a novel and challenging dataset for radar detection (RadDet), comprising a large corpus of radar signals occupying a wideband spectrum across diverse radar density environments and signal-to-noise ratios (SNR).
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models
Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues.
Color-Oriented Redundancy Reduction in Dataset Distillation
At the image level, we employ a palette network, a specialized neural network, to dynamically allocate colors from a reduced color space to each pixel.
Track Any Peppers: Weakly Supervised Sweet Pepper Tracking Using VLMs
In the Detection and Multi-Object Tracking of Sweet Peppers Challenge, we present Track Any Peppers (TAP) - a weakly supervised ensemble technique for sweet peppers tracking.
Is Less More? Exploring Token Condensation as Training-free Adaptation for CLIP
To address these questions, we propose Token Condensation as Adaptation (TCA), a training-free adaptation method for CLIP by pruning class-irrelevant visual tokens while merging class-ambiguous tokens.
CF-PRNet: Coarse-to-Fine Prototype Refining Network for Point Cloud Completion and Reconstruction
In modern agriculture, precise monitoring of plants and fruits is crucial for tasks such as high-throughput phenotyping and automated harvesting.
PlantSeg: A Large-Scale In-the-wild Dataset for Plant Disease Segmentation
(2) Image source: Unlike typical datasets that contain images from laboratory settings, PlantSeg primarily comprises in-the-wild plant disease images.
FastEdit: Fast Text-Guided Single-Image Editing via Semantic-Aware Diffusion Fine-Tuning
It can effectively align the target text prompt and input image within the same feature space and save substantial processing time.
Benchmarking In-the-wild Multimodal Disease Recognition and A Versatile Baseline
Motivated by this observation, we propose an in-the-wild multimodal plant disease recognition dataset that contains the largest number of disease classes but also text-based descriptions for each disease.
Navigating Beyond Instructions: Vision-and-Language Navigation in Obstructed Environments
Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities.
Physics-guided Active Sample Reweighting for Urban Flow Prediction
Moreover, due to the interval-based predictions and intermittent nature of data filing in many transportation services, the instantaneous dynamics of urban flows can hardly be captured, rendering differential equation-based continuous modeling a loose fit for this setting.
A Thorough Performance Benchmarking on Lightweight Embedding-based Recommender Systems
State-of-the-art RSs primarily depend on categorical features, which ecoded by embedding vectors, resulting in excessively large embedding tables.
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Specifically, we propose a Model Synergy (MOS) strategy that dynamically selects historical checkpoints with diverse knowledge and assembles them to best accommodate the current test batch.
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
We demonstrate the effectiveness of DiPEx through extensive class-agnostic OD and OOD-OD experiments on MS-COCO and LVIS, surpassing other prompting methods by up to 20. 1% in AR and achieving a 21. 3% AP improvement over SAM.
DPO: Dual-Perturbation Optimization for Test-time Adaptation in 3D Object Detection
We minimize the sharpness to cultivate a flat loss landscape to ensure model resiliency to minor data variations, thereby enhancing the generalization of the adaptation process.
GaussianForest: Hierarchical-Hybrid 3D Gaussian Splatting for Compressed Scene Modeling
The field of novel-view synthesis has recently witnessed the emergence of 3D Gaussian Splatting, which represents scenes in a point-based manner and renders through rasterization.
Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts
Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents.
GCondenser: Benchmarking Graph Condensation
Large-scale graphs are valuable for graph representation learning, yet the abundant data in these graphs hinders the efficiency of the training process.
CaseGNN++: Graph Contrastive Learning for Legal Case Retrieval with Graph Augmentation
Specifically, an edge feature-based graph attention layer (EUGAT) is proposed to comprehensively update node and edge features during graph modelling, resulting in a full utilisation of structural information of legal cases.
Universal Adversarial Perturbations for Vision-Language Pre-trained Models
To this end, we propose a novel black-box method to generate Universal Adversarial Perturbations (UAPs), which is so called the Effective and T ransferable Universal Adversarial Attack (ETU), aiming to mislead a variety of existing VLP models in a range of downstream tasks.
Effective and Robust Adversarial Training against Data and Label Corruptions
We propose a hybrid adversarial training surrounding multiple potential adversarial perturbations, alongside a semi-supervised learning based on class- rebalancing sample selection to enhance the resilience of the model for dual corruption.
CaseLink: Inductive Graph Learning for Legal Case Retrieval
In a case pool, there are three types of case connectivity relationships: the case reference relationship, the case semantic relationship, and the case legal charge relationship.
Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments
In this work, we tackle the limitations of current LiDAR-based 3D object detection systems, which are hindered by a restricted class vocabulary and the high costs associated with annotating new object classes.
Automatic Radar Signal Detection and FFT Estimation using Deep Learning
This paper addresses a critical preliminary step in radar signal processing: detecting the presence of a radar signal and robustly estimating its bandwidth.
PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation
Although the CaT alleviates the catastrophic forgetting problem, there exist three issues: (1) The graph condensation only focuses on labelled nodes while neglecting abundant information carried by unlabelled nodes; (2) The continual training scheme of the CaT overemphasises on the previously learned knowledge, limiting the model capacity to learn from newly added memories; (3) Both the condensation process and replaying process of the CaT are time-consuming.
CaseGNN: Graph Neural Networks for Legal Case Retrieval with Text-Attributed Graphs
Previous neural legal case retrieval models mostly encode the unstructured raw text of case into a case representation, which causes the lack of important legal structural information in a case and leads to poor case representation; (2) Lengthy legal text limitation.
Multi-stage Learning for Radar Pulse Activity Segmentation
Radio signal recognition is a crucial function in electronic warfare.
OpenSight: A Simple Open-Vocabulary Framework for LiDAR-Based Object Detection
OpenSight utilizes 2D-3D geometric priors for the initial discernment and localization of generic objects, followed by a more specific semantic interpretation of the detected objects.
Learning Efficient Unsupervised Satellite Image-based Building Damage Detection
Existing Building Damage Detection (BDD) methods always require labour-intensive pixel-level annotations of buildings and their conditions, hence largely limiting their applications.
In Search of Lost Online Test-time Adaptation: A Survey
This article presents a comprehensive survey of online test-time adaptation (OTTA), focusing on effectively adapting machine learning models to distributionally different target data upon batch arrival.
Understanding the Effects of Projectors in Knowledge Distillation
Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance.
Open-CRB: Towards Open World Active Learning for 3D Object Detection
This paper investigates a more practical and challenging research task: Open World Active Learning for 3D Object Detection (OWAL-3D), aimed at acquiring informative point clouds with new concepts.
Divide and Ensemble: Progressively Learning for the Unknown
In the wheat nutrient deficiencies classification challenge, we present the DividE and EnseMble (DEEM) method for progressive test data predictions.
CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
Analyzing model performance in various unseen environments is a critical research problem in the machine learning community.
CaT: Balanced Continual Graph Learning with Graph Condensation
Recent replay-based methods intend to solve this problem by updating the model using both (1) the entire new-coming data and (2) a sampling-based memory bank that stores replayed graphs to approximate the distribution of historical data.
UQ at #SMM4H 2023: ALEX for Public Health Analysis with Social Media
As social media becomes increasingly popular, more and more activities related to public health emerge.
BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge
In a nutshell, our BAVS is designed to eliminate the interference of background noise or off-screen sounds in segmentation by establishing the audio-visual correspondences in an explicit manner.
Cal-SFDA: Source-Free Domain-adaptive Semantic Segmentation with Differentiable Expected Calibration Error
The prevalence of domain adaptive semantic segmentation has prompted concerns regarding source domain data leakage, where private information from the source domain could inadvertently be exposed in the target domain.
OrcoDCS: An IoT-Edge Orchestrated Online Deep Compressed Sensing Framework
However, the existing compressed data aggregation (CDA) frameworks (e. g., compressed sensing-based data aggregation, deep learning(DL)-based data aggregation) do not possess the flexibility and adaptivity required to handle distinct sensing tasks and environmental changes.
Zero-Shot Learning by Harnessing Adversarial Samples
To take the advantage of image augmentations while mitigating the semantic distortion issue, we propose a novel ZSL approach by Harnessing Adversarial Samples (HAS).
KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection
Achieving a reliable LiDAR-based object detector in autonomous driving is paramount, but its success hinges on obtaining large amounts of precise 3D annotations.
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.
Multi-task Learning for Radar Signal Characterisation
Radio signal recognition is a crucial task in both civilian and military applications, as accurate and timely identification of unknown signals is an essential part of spectrum management and electronic warfare.
Explicit Knowledge Graph Reasoning for Conversational Recommendation
Recent conversational recommender systems (CRSs) tackle those limitations by enabling recommender systems to interact with the user to obtain her/his current preference through a sequence of clarifying questions.
Semi-decentralized Federated Ego Graph Learning for Recommendation
In light of this, we propose a semi-decentralized federated ego graph learning framework for on-device recommendations, named SemiDFEGL, which introduces new device-to-device collaborations to improve scalability and reduce communication costs and innovatively utilizes predicted interacted item nodes to connect isolated ego graphs to augment local subgraphs such that the high-order user-item collaborative information could be used in a privacy-preserving manner.
Exploring Active 3D Object Detection from a Generalization Perspective
To alleviate the high annotation cost in LiDAR-based 3D object detection, active learning is a promising solution that learns to select only a small portion of unlabeled data to annotate, without compromising model performance.
Object-Goal Visual Navigation via Effective Exploration of Relations Among Historical Navigation States
In HiNL, we propose a History-aware State Estimation (HaSE) module to alleviate the impacts of dominant historical states on the current state estimation.
How Far Pre-trained Models Are from Neural Collapse on the Target Dataset Informs their Transferability
This paper focuses on model transferability estimation, i. e., assessing the performance of pre-trained models on a downstream task without performing fine-tuning.
Improved Feature Distillation via Projector Ensemble
Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features.
Self-supervised Graph-based Point-of-interest Recommendation
In order to counteract the scarcity and incompleteness of POI check-ins, we propose a novel self-supervised learning paradigm in \ssgrec, where the trajectory representations are contrastively learned from two augmented views on geolocations and temporal transitions.
Beyond Double Ascent via Recurrent Neural Tangent Kernel in Sequential Recommendation
In this paper, we propose the Overparameterised Recommender (OverRec), which utilises a recurrent neural tangent kernel (RNTK) as a similarity measurement for user sequences to successfully bypass the restriction of hardware for huge models.
Federated Zero-Shot Learning for Visual Recognition
We identify two key challenges in our FedZSL protocol: 1) the trained models are prone to be biased to the locally observed classes, thus failing to generalize to the unseen classes and/or seen classes appeared on other devices; 2) as each category in the training data comes from a single source, the central model is highly vulnerable to model replacement (backdoor) attacks.
Discovering Domain Disentanglement for Generalized Multi-source Domain Adaptation
A typical multi-source domain adaptation (MSDA) approach aims to transfer knowledge learned from a set of labeled source domains, to an unlabeled target domain.
GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning
To address this issue, we propose a novel flow-based generative framework that consists of multiple conditional affine coupling layers for learning unseen data generation.
Self-Supervised Learning for Recommender Systems: A Survey
In recent years, neural architecture-based recommender systems have achieved tremendous success, but they still fall short of expectation when dealing with highly sparse data.
Source-Free Progressive Graph Learning for Open-Set Domain Adaptation
However, most existing OSDA approaches are limited due to three main reasons, including: (1) the lack of essential theoretical analysis of generalization bound, (2) the reliance on the coexistence of source and target data during adaptation, and (3) failing to accurately estimate the uncertainty of model predictions.
DeHIN: A Decentralized Framework for Embedding Large-scale Heterogeneous Information Networks
Such heterogeneous network embedding (HNE) methods effectively harness the heterogeneity of small-scale HINs.
N-Cloth: Predicting 3D Cloth Deformation with Mesh-Based Networks
We present a novel mesh-based learning approach (N-Cloth) for plausible 3D cloth deformation prediction.
PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion
Evaluations on two real-world datasets show that 1) our attack model significantly boosts the exposure rate of the target item in a stealthy way, without harming the accuracy of the poisoned recommender; and 2) existing defenses are not effective enough, highlighting the need for new defenses against our local model poisoning attacks to federated recommender systems.
Domain Adaptive Semantic Segmentation without Source Data
To address these problems, we investigate domain adaptive semantic segmentation without source data, which assumes that the model is pre-trained on the source domain, and then adapting to the target domain without accessing source data anymore.
Contrastive Learning for Representation Degeneration Problem in Sequential Recommendation
In this paper, both empirical and theoretical investigations of this representation degeneration problem are first provided, based on which a novel recommender model DuoRec is proposed to improve the item embeddings distribution.
Memory Augmented Multi-Instance Contrastive Predictive Coding for Sequential Recommendation
In this paper, we propose a novel sequential recommendation framework to overcome these challenges based on a memory augmented multi-instance contrastive predictive coding scheme, denoted as MMInfoRec.
Learning to Diversify for Single Domain Generalization
Domain generalization (DG) aims to generalize a model trained on multiple source (i. e., training) domains to a distributionally different target (i. e., test) domain.
Ranked #7 on
Single-Source Domain Generalization
on Digits-five
Mitigating Generation Shifts for Generalized Zero-Shot Learning
Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e. g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training.
CausalRec: Causal Inference for Visual Debiasing in Visually-Aware Recommendation
Existing visually-aware models make use of the visual features as a separate collaborative signal similarly to other features to directly predict the user's preference without considering a potential bias, which gives rise to a visually biased recommendation.
Attribute-aware Explainable Complementary Clothing Recommendation
As a result, this creates a severe bottleneck when we are trying to advance the recommendation accuracy and generating fine-grained explanations since the explicit attributes have only loose connections to the actual recommendation process.
Exploiting Positional Information for Session-based Recommendation
According to our analysis, existing positional encoding schemes are generally forward-aware only, which can hardly represent the dynamics of the intention in a session.
Exploiting Cross-Session Information for Session-based Recommendation with Graph Neural Networks
Different from the traditional recommender system, the session-based recommender system introduces the concept of the session, i. e., a sequence of interactions between a user and multiple items within a period, to preserve the user's recent interest.
Discovering Collaborative Signals for Next POI Recommendation with Iterative Seq2Graph Augmentation
Furthermore, the sparse POI-POI transitions restrict the ability of a model to learn effective sequential patterns for recommendation.
Learning Elastic Embeddings for Customizing On-Device Recommenders
The core idea is to compose elastic embeddings for each item, where an elastic embedding is the concatenation of a set of embedding blocks that are carefully chosen by an automated search function.
Learning to Ask Appropriate Questions in Conversational Recommendation
Hence, the ability to generate suitable clarifying questions is the key to timely tracing users' dynamic preferences and achieving successful recommendations.
Quaternion Factorization Machines: A Lightweight Solution to Intricate Feature Interaction Modelling
As a well-established approach, factorization machine (FM) is capable of automatically learning high-order interactions among features to make predictions without the need for manual feature engineering.
Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
In WIDEN, we propose a novel inductive, meta path-free message passing scheme that packs up heterogeneous node features with their associated edges from both low- and high-order neighbor nodes.
Enhanced Modality Transition for Image Captioning
In this work, we explicitly build a Modality Transition Module (MTM) to transfer visual features into semantic representations before forwarding them to the language model.
Graph Embedding for Recommendation against Attribute Inference Attacks
Specifically, in GERAI, we bind the information perturbation mechanism in differential privacy with the recommendation capability of graph convolutional networks.
Semantics Disentangling for Generalized Zero-Shot Learning
Generalized zero-shot learning (GZSL) aims to classify samples under the assumption that some classes are not observable during training.
Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning
To address these issues, in this paper, we propose a novel framework that leverages dual variational autoencoders with a triplet loss to learn discriminative latent features and applies the entropy-based calibration to minimize the uncertainty in the overlapped area between the seen and unseen classes.
Interpretable Signed Link Prediction with Signed Infomax Hyperbolic Graph
Most of the prior efforts are devoted to learning node embeddings with graph neural networks (GNNs), which preserve the signed network topology by message-passing along edges to facilitate the downstream link prediction task.
Adversarial Bipartite Graph Learning for Video Domain Adaptation
To further enhance the model capacity and testify the robustness of the proposed architecture on difficult transfer tasks, we extend our model to work in a semi-supervised setting using an additional video-level bipartite graph.
Ranked #3 on
Domain Adaptation
on HMDB --> UCF (full)
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
A voting strategy averages the probability distributions output from the classifiers and, given that some patches are more discriminative than others, a discrimination-based attention mechanism helps to weight each patch accordingly.
GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
On one hand, when a new session arrives, a session graph with a global attribute is constructed based on the current session and its associate user.
Progressive Graph Learning for Open-Set Domain Adaptation
The existing domain adaptation approaches which tackle this problem work in the closed-set setting with the assumption that the source and the target data share exactly the same classes of objects.
ORD: Object Relationship Discovery for Visual Dialogue Generation
With the rapid advancement of image captioning and visual question answering at single-round level, the question of how to generate multi-round dialogue about visual content has not yet been well explored. Existing visual dialogue methods encode the image into a fixed feature vector directly, concatenated with the question and history embeddings to predict the response. Some recent methods tackle the co-reference resolution problem using co-attention mechanism to cross-refer relevant elements from the image, history, and the target question. However, it remains challenging to reason visual relationships, since the fine-grained object-level information is omitted before co-attentive reasoning.
GCN-Based User Representation Learning for Unifying Robust Recommendation and Fraudster Detection
Therefore, it is of great practical significance to construct a robust recommender system that is able to generate stable recommendations even in the presence of shilling attacks.
Try This Instead: Personalized and Interpretable Substitute Recommendation
Then, by treating attributes as the bridge between users and items, we can thoroughly model the user-item preferences (i. e., personalization) and item-item relationships (i. e., substitution) for recommendation.
Suicidal Ideation and Mental Disorder Detection with Attentive Relation Networks
Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without effective treatment.
Enhancing Social Recommendation with Adversarial Graph Convolutional Networks
Social recommender systems are expected to improve recommendation quality by incorporating social information when there is little user-item interaction data.
Rethinking the Item Order in Session-based Recommendation with Graph Neural Networks
In this paper, therefore, we study the item transition pattern by constructing a session graph and propose a novel model which collaboratively considers the sequence order and the latent order in the session graph for a session-based recommender system.
Learning from the Past: Continual Meta-Learning via Bayesian Graph Modeling
Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data.
Deep Collaborative Discrete Hashing with Semantic-Invariant Structure
Existing deep hashing approaches fail to fully explore semantic correlations and neglect the effect of linguistic context on visual attention learning, leading to inferior performance.
Suicidal Ideation Detection: A Review of Machine Learning Methods and Applications
Suicide is a critical issue in modern society.
CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Language
Thus, a multi-modal cycle-consistency loss between the synthesized semantic representations and the ground truth can be learned and leveraged to enforce the generated semantic features to approximate to the real distribution in semantic space.
Alleviating Feature Confusion for Generative Zero-shot Learning
An inevitable issue of such a paradigm is that the synthesized unseen features are prone to seen references and incapable to reflect the novelty and diversity of real unseen instances.
Cycle-consistent Conditional Adversarial Transfer Networks
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions.
Ranked #4 on
Domain Adaptation
on USPS-to-MNIST
Curiosity-driven Reinforcement Learning for Diverse Visual Paragraph Generation
Visual paragraph generation aims to automatically describe a given image from different perspectives and organize sentences in a coherent way.
Agile Domain Adaptation
Because of the distribution shifts, different target samples have distinct degrees of difficulty in adaptation.
From Zero-Shot Learning to Cold-Start Recommendation
This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR.
Exploring Auxiliary Context: Discrete Semantic Transfer Hashing for Scalable Image Retrieval
To address the problem, in this paper, we propose a novel hashing approach, dubbed as \emph{Discrete Semantic Transfer Hashing} (DSTH).
Leveraging the Invariant Side of Generative Zero-Shot Learning
In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions.
Ranked #5 on
Generalized Zero-Shot Learning
on SUN Attribute
Snap and Find: Deep Discrete Cross-domain Garment Image Retrieval
With the increasing number of online stores, there is a pressing need for intelligent search systems to understand the item photos snapped by customers and search against large-scale product databases to find their desired items.
SADIH: Semantic-Aware DIscrete Hashing
Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications.
Learning Private Neural Language Modeling with Attentive Aggregation
Federated learning (FL) provides a promising approach to learning private language modeling for intelligent personalized keyboard suggestion by training models in distributed clients rather than training in a central server.
Look Deeper See Richer: Depth-aware Image Paragraph Captioning
Existing image paragraph captioning methods give a series of sentences to represent the objects and regions of interests, where the descriptions are essentially generated by feeding the image fragments containing objects and regions into conventional image single-sentence captioning models.
Collaborative Learning for Extremely Low Bit Asymmetric Hashing
Hashing techniques are in great demand for a wide range of real-world applications such as image retrieval and network compression.
Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning
Rich high-quality annotated data is critical for semantic segmentation learning, yet acquiring dense and pixel-wise ground-truth is both labor- and time-consuming.
Leveraging Weak Semantic Relevance for Complex Video Event Classification
In this paper, we propose a novel approach to automatically maximize the utility of weak semantic annotations (formalized as the semantic relevance of video shots to the target event) to facilitate video event classification.
Discrete Multi-modal Hashing with Canonical Views for Robust Mobile Landmark Search
Finally, compact binary codes are learned on intermediate representation within a tailored discrete binary embedding model which preserves visual relations of images measured with canonical views and removes the involved noises.
Multi-Attention Network for One Shot Learning
One-shot learning is a challenging problem where the aim is to recognize a class identified by a single training image.
From Community Detection to Community Profiling
Most existing community-related studies focus on detection, which aim to find the community membership for each user from user friendship links.
Binary Subspace Coding for Query-by-Image Video Retrieval
The first approach, termed Inner-product Binary Coding (IBC), preserves the inner relationships of images and videos in a common Hamming space.
Where to Focus: Query Adaptive Matching for Instance Retrieval Using Convolutional Feature Maps
Instance retrieval requires one to search for images that contain a particular object within a large corpus.
Bidirectional Long-Short Term Memory for Video Description
Video captioning has been attracting broad research attention in multimedia community.
What's Wrong With That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution
The key observation motivating our approach is that "regular object" images, "unusual object" images and "other objects" images exhibit different region-level scores in terms of both the score values and the spatial distributions.
