Search Results for author:
Found 45 papers, 21 papers with code
Toward Knowledge-Enriched Conversational Recommendation Systems
Conversational Recommendation Systems recommend items through language based interactions with users. In order to generate naturalistic conversations and effectively utilize knowledge graphs (KGs) containing background information, we propose a novel Bag-of-Entities loss, which encourages the generated utterances to mention concepts related to the item being recommended, such as the genre or director of a movie.
Learning Remote Sensing Object Detection with Single Point Supervision
In this paper, we make the first attempt to achieve RS object detection with single point supervision, and propose a PSOD framework tailored with RS images.
InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pre-trained BLIP-2 models.
Movie Box Office Prediction With Self-Supervised and Visually Grounded Pretraining
Investments in movie production are associated with a high level of risk as movie revenues have long-tailed and bimodal distributions.
Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection
The core idea of this work is to recover the per-pixel mask of each target from the given single point label by using clustering approaches, which looks simple but is indeed challenging since targets are always insalient and accompanied with background clutters.
History-Aware Hierarchical Transformer for Multi-session Open-domain Dialogue System
HAHT maintains a long-term memory of history conversations and utilizes history information to understand current conversation context and generate well-informed and context-relevant responses.
From Images to Textual Prompts: Zero-Shot Visual Question Answering With Frozen Large Language Models
To address this issue, we propose Img2Prompt, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training.
From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models
To address this issue, we propose \emph{Img2Prompt}, a plug-and-play module that provides the prompts that can bridge the aforementioned modality and task disconnections, so that LLMs can perform zero-shot VQA tasks without end-to-end training.
Is GPT-3 a Good Data Annotator?
In this paper, we evaluate the performance of GPT-3 as a data annotator by comparing it with traditional data annotation methods and analyzing its output on a range of tasks.
Mitigating and Evaluating Static Bias of Action Representations in the Background and the Foreground
In video action recognition, shortcut static features can interfere with the learning of motion features, resulting in poor out-of-distribution (OOD) generalization.
A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculture
In addition, we discuss five key subareas of computer vision and how they related to these CEA problems, as well as nine vision-based CEA datasets.
Plug-and-Play VQA: Zero-shot VQA by Conjoining Large Pretrained Models with Zero Training
Visual question answering (VQA) is a hallmark of vision and language reasoning and a challenging task under the zero-shot setting.
Ranked #5 on
Visual Question Answering (VQA)
on VQA v2 val
Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation
Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP tasks.
MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.
Minimalist and High-performance Conversational Recommendation with Uncertainty Estimation for User Preference
Multi-shot CRS is designed to make recommendations multiple times until the user either accepts the recommendation or leaves at the end of their patience.
Efficient Self-supervised Vision Pretraining with Local Masked Reconstruction
After finetuning the pretrained LoMaR on 384$\times$384 images, it can reach 85. 4% top-1 accuracy, surpassing MAE by 0. 6%.
A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensus
In many recent novel blockchain consensuses, the deep learning training procedure becomes the task for miners to prove their workload, thus the computation power of miners will not purely be spent on the hash puzzle.
Synopses of Movie Narratives: a Video-Language Dataset for Story Understanding
Despite recent advances of AI, story understanding remains an open and under-investigated problem.
Improving Tail-Class Representation with Centroid Contrastive Learning
ICCL interpolates two images from a class-agnostic sampler and a class-aware sampler, and trains the model such that the representation of the interpolative image can be used to retrieve the centroids for both source classes.
Ranked #20 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Noise-Resistant Deep Metric Learning with Probabilistic Instance Filtering
Noisy labels are commonly found in real-world data, which cause performance degradation of deep neural networks.
Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems
In this work, we propose a new initialization scheme for user and item embeddings called Laplacian Eigenmaps with Popularity-based Regularization for Isolated Data (LEPORID).
Dense Nested Attention Network for Infrared Small Target Detection
With the repeated interaction in DNIM, infrared small targets in deep layers can be maintained.
Non-Convex Tensor Low-Rank Approximation for Infrared Small Target Detection
Considering that different singular values have different importance and should be treated discriminatively, in this paper, we propose a non-convex tensor low-rank approximation (NTLA) method for infrared small target detection.
Seastar: vertex-centric programming for graph neural networks
Graph neural networks (GNNs) have achieved breakthrough performance in graph analytics such as node classification, link prediction and graph clustering.
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection
The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality.
Noise-resistant Deep Metric Learning with Ranking-based Instance Selection
The existence of noisy labels in real-world data negatively impacts the performance of deep learning models.
VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning
To the best of our knowledge, this is the first work that improves data efficiency of image captioning by utilizing LM pretrained on unimodal data.
HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
the weights of training data, HYDRA assesses the contribution of training data toward test data points throughout the training trajectory.
Federated Learning for Personalized Humor Recognition
In this paper, we propose the FedHumor approach for the recognition of humorous content in a personalized manner through Federated Learning (FL).
Data-efficient Alignment of Multimodal Sequences by Aligning Gradient Updates and Internal Feature Distributions
The task of video and text sequence alignment is a prerequisite step toward joint understanding of movie videos and screenplays.
Proof of Learning (PoLe): Empowering Machine Learning with Consensus Building on Blockchains
Empirical evaluation shows that SML can detect cheating nodes at small cost to the predictive performance.
Exploring Long Tail Visual Relationship Recognition with Large Vocabulary
We use these benchmarks to study the performance of several state-of-the-art long-tail models on the LTVRR setup.
Searching for Stage-wise Neural Graphs In the Limit
Search space is a key consideration for neural architecture search.
An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations.
NormLime: A New Feature Importance Metric for Explaining Deep Neural Networks
The problem of explaining deep learning models, and model predictions generally, has attracted intensive interest recently.
Real-Time Adversarial Attacks
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail.
DLBC: A Deep Learning-Based Consensus in Blockchains for Deep Learning Services
In this paper, we propose DLBC to exploit the computation power of miners for deep learning training as proof of useful work instead of calculating hash values.
A Multi-task Neural Approach for Emotion Attribution, Classification and Summarization
However, the sparsity of emotional expressions in the videos poses an obstacle to visual emotion analysis.
Understanding Actors and Evaluating Personae with Gaussian Embeddings
Understanding narrative content has become an increasingly popular topic.
Joint Event Detection and Description in Continuous Video Streams
In order to explicitly model temporal relationships between visual events and their captions in a single video, we also propose a two-level hierarchical captioning module that keeps track of context.
A Neural Multi-sequence Alignment TeCHnique (NeuMATCH)
The alignment of heterogeneous sequential data (video to text) is an important and challenging problem.
Annotating High-Level Structures of Short Stories and Personal Anecdotes
Stories are a vital form of communication in human culture; they are employed daily to persuade, to elicit sympathy, or to convey a message.
Cultural Vocal Bursts Intensity Prediction
Vocal Bursts Intensity Prediction
Predicting the Quality of Short Narratives from Social Media
An important and difficult challenge in building computational models for narratives is the automatic evaluation of narrative quality.
Heterogeneous Knowledge Transfer in Video Emotion Recognition, Attribution and Summarization
Emotion is a key element in user-generated videos.
