Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleJuly 2024
LDRE: LLM-based Divergent Reasoning and Ensemble for Zero-Shot Composed Image Retrieval
SIGIR '24: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information RetrievalJuly 2024, Pages 80–90https://doi.org/10.1145/3626772.3657740Zero-Shot Composed Image Retrieval (ZS-CIR) has garnered increasing interest in recent years, which aims to retrieve a target image based on a query composed of a reference image and a modification text without training samples. Specifically, the ...
- short-paperJuly 2024
Is GPT-4 Alone Sufficient for Automated Essay Scoring?: A Comparative Judgment Approach Based on Rater Cognition
L@S '24: Proceedings of the Eleventh ACM Conference on Learning @ ScaleJuly 2024, Pages 315–319https://doi.org/10.1145/3657604.3664703Large Language Models (LLMs) have shown promise in Automated Essay Scoring (AES), but their zero-shot and few-shot performance often falls short compared to state-of-the-art models and human raters. However, fine-tuning LLMs for each specific task is ...
- ArticleJuly 2024
Target-Phrase Zero-Shot Stance Detection: Where Do We Stand?
AbstractStance detection, i.e. recognition of utterances in favor, against or neutral in relation to some targets is important for text analysis. However, different approaches were tested on different datasets, often interpreted in different ways. We ...
- research-articleJune 2024
RAPID: Zero-Shot Domain Adaptation for Code Search with Pre-Trained Models
ACM Transactions on Software Engineering and Methodology (TOSEM), Volume 33, Issue 5Article No.: 128, Pages 1–35https://doi.org/10.1145/3641542Code search, which refers to the process of identifying the most relevant code snippets for a given natural language query, plays a crucial role in software maintenance. However, current approaches heavily rely on labeled data for training, which results ...
- research-articleMay 2024
Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 4407–4416https://doi.org/10.1145/3589334.3645678Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of fully labeled ...
-
- research-articleMay 2024
Multi-Label Zero-Shot Product Attribute-Value Extraction
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 2259–2270https://doi.org/10.1145/3589334.3645649E-commerce platforms should provide detailed product descriptions (attribute values) for effective product search and recommendation. However, attribute value information is typically not available for new products. To predict unseen attribute values, ...
- research-articleMay 2024
Zero-shot Image Classification with Logic Adapter and Rule Prompt
WWW '24: Proceedings of the ACM on Web Conference 2024May 2024, Pages 2075–2084https://doi.org/10.1145/3589334.3645554Zero-shot image classification, which aims to predict unseen classes whose samples have never appeared during the training phase, is crucial in the Web domain because many new web images appear on various websites. Attributes, as annotations for class-...
- research-articleApril 2024
Generalized Weak Supervision for Neural Information Retrieval
ACM Transactions on Information Systems (TOIS), Volume 42, Issue 5Article No.: 121, Pages 1–26https://doi.org/10.1145/3647639Neural ranking models (NRMs) have demonstrated effective performance in several information retrieval (IR) tasks. However, training NRMs often requires large-scale training data, which is difficult and expensive to obtain. To address this issue, one can ...
- research-articleJune 2024
Investigating the Efficacy of Large Language Models for Code Clone Detection
ICPC '24: Proceedings of the 32nd IEEE/ACM International Conference on Program ComprehensionApril 2024, Pages 161–165https://doi.org/10.1145/3643916.3645030Large Language Models (LLMs) have demonstrated remarkable success in various natural language processing and software engineering tasks, such as code generation. The LLMs are mainly utilized in the prompt-based zero/few-shot paradigm to guide the model ...
- ArticleApril 2024
Leveraging Panoptic Prior for 3D Zero-Shot Semantic Understanding Within Language Embedded Radiance Fields
AbstractLanguage Embedded Radiance Fields (LERF) achieves promising results in real-time dense relevancy maps within NeRF 3D scenes. Although LERF shows impressive zero-shot ability in many long-tail open-vocabulary queries, the quality of relevancy maps ...
- research-articleApril 2024
Language Models in the Loop: Incorporating Prompting into Weak Supervision
ACM / IMS Journal of Data Science (JDS), Volume 1, Issue 2Article No.: 7, Pages 1–30https://doi.org/10.1145/3617130We propose a new strategy for applying large pre-trained language models to novel tasks when labeled training data is limited. Rather than apply the model in a typical zero-shot or few-shot fashion, we treat the model as the basis for labeling functions ...
HighlightsProblem statement
The goal of this paper is to use large language models to create smaller, specialized models. These specialized models can be better suited to specific tasks because they are tuned for them and are less expensive to serve in ...
- extended-abstractMarch 2024
Multi-Granular Text Classification with Minimal Supervision
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningMarch 2024, Pages 1158–1160https://doi.org/10.1145/3616855.3635735Our society has been immersed with massive unstructured text data, posing great challenges for people to fetch needed data, digest critical information, and derive actionable knowledge. Such needs necessitate the development of text classification which ...
- short-paperOctober 2023
Zero-Shot Learning for Computer Vision Applications
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 9360–9364https://doi.org/10.1145/3581783.3613435Human beings possess the remarkable ability to recognize unseen concepts by integrating their visual perception of known concepts with some high-level descriptions. However, the best-performing deep learning frameworks today are supervised learners that ...
- research-articleOctober 2023
SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 8157–8166https://doi.org/10.1145/3581783.3612661Food detection is becoming a fundamental task in food computing that supports various multimedia applications, including food recommendation and dietary monitoring. To deal with real-world scenarios, food detection needs to localize and recognize novel ...
- research-articleOctober 2023
Zero-Shot Object Detection by Semantics-Aware DETR with Adaptive Contrastive Loss
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 4421–4430https://doi.org/10.1145/3581783.3612523Zero-shot object detection (ZSD) aims to localize and recognize unseen objects in unconstrained images by leveraging semantic descriptions. Existing ZSD methods typically suffer from two drawbacks: 1) Due to the lack of data on unseen categories during ...
- research-articleOctober 2023
Bridging Language and Geometric Primitives for Zero-shot Point Cloud Segmentation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 5380–5388https://doi.org/10.1145/3581783.3612409We investigate transductive zero-shot point cloud semantic segmentation, where the network is trained on seen objects and able to segment unseen objects. The 3D geometric elements are essential cues to imply a novel 3D object type. However, previous ...
- research-articleOctober 2023
Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 3745–3754https://doi.org/10.1145/3581783.3612107Traditional 3D segmentation methods can only recognize a fixed range of classes that appear in the training set, which limits their application in real-world scenarios due to the lack of generalization ability. Large-scale visual-language pre-trained ...
- research-articleOctober 2023
M3R: Masked Token Mixup and Cross-Modal Reconstruction for Zero-Shot Learning
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 3161–3171https://doi.org/10.1145/3581783.3612104In the zero-shot learning (ZSL), learned representation spaces are often biased toward seen classes, thus limiting the ability to predict previously unseen classes. In this paper, we propose Masked token Mixup and cross-Modal Reconstruction for zero-shot ...
- research-articleOctober 2023
Frequency-based Zero-Shot Learning with Phase Augmentation
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 3181–3189https://doi.org/10.1145/3581783.3611990Zero-Shot Learning (ZSL) aims to recognize images from seen and unseen classes by aligning visual and semantic knowledge (e.g., attribute descriptions). However, the fine-grained attributes in the RGB domain can be easily affected by background noise (...
- research-articleOctober 2023
Zero-shot Skeleton-based Action Recognition via Mutual Information Estimation and Maximization
MM '23: Proceedings of the 31st ACM International Conference on MultimediaOctober 2023, Pages 5302–5310https://doi.org/10.1145/3581783.3611888Zero-shot skeleton-based action recognition aims to recognize actions of unseen categories after training on data of seen categories. The key is to build the connection between visual and semantic space from seen to unseen classes. Previous studies have ...