相关论文: First Place Solution of 2023 Global Artificial Int…
As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks. This paper presents our 3rd place solution to the matching track of Image Similarity Challenge (ISC) 2021…
In this work, we address the challenge of multilingual category relevance judgment in e-commerce search, where traditional ensemble-based systems improve accuracy but at the cost of heavy training, inference, and maintenance complexity. To…
This paper presents a data-free, parameter-isolation-based continual learning algorithm we developed for the sequential task continual learning track of the 2nd Greater Bay Area International Algorithm Competition. The method learns an…
This paper presents our 3rd place solution in both Descriptor Track and Matching Track of the Meta AI Video Similarity Challenge (VSC2022), a competition aimed at detecting video copies. Our approach builds upon existing image copy…
Evaluation of text-to-music systems is constrained by the cost and availability of collecting experts for assessment. AudioMOS 2025 Challenge track 1 is created to automatically predict music impression (MI) as well as text alignment (TA)…
Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world relevance. We introduce CleanPatrick, the first large-scale…
The Science4cast 2021 competition focuses on predicting future edges in an evolving semantic network, where each vertex represents an artificial intelligence concept, and an edge between a pair of vertices denotes that the two concepts have…
Effective prioritization of issue reports is crucial in software engineering to optimize resource allocation and address critical problems promptly. However, the manual classification of issue reports for prioritization is laborious and…
In this paper, we show our solution to the Google Landmark Recognition 2021 Competition. Firstly, embeddings of images are extracted via various architectures (i.e. CNN-, Transformer- and hybrid-based), which are optimized by ArcFace loss.…
The ACM RecSys Challenge 2023, organized by ShareChat, aims to predict the probability of the app being installed. This paper describes the lightweight solution to this challenge. We formulate the task as a user response prediction task.…
Competitive programming benchmarks are widely used in scenarios such as programming contests and large language model assessments. However, the growing presence of duplicate or highly similar problems raises concerns not only about…
Affordance-Centric Question-driven Task Completion (AQTC) has been proposed to acquire knowledge from videos to furnish users with comprehensive and systematic instructions. However, existing methods have hitherto neglected the necessity of…
A leaderboard is a tabular presentation of performance scores of the best competing techniques that address a specific scientific problem. Manually maintained leaderboards take time to emerge, which induces a latency in performance…
In this paper, we describe the solution to the QQ Browser 2021 Ai Algorithm Competition (AIAC) Track 1. We use the multi-modal transformer model for the video embedding extraction. In the pretrain phase, we train the model with three tasks,…
This paper presents the 1st place solution to the Google Landmark Retrieval 2020 Competition on Kaggle. The solution is based on metric learning to classify numerous landmark classes, and uses transfer learning with two train datasets,…
This work uses the state-of-the-art language model GPT-3 to offer a novel method of information extraction for knowledge base development. The suggested method attempts to solve the difficulties associated with obtaining relevant entities…
Recent immense breakthroughs in generative models such as in GPT4 have precipitated re-imagined ubiquitous usage of these models in all applications. One area that can benefit by improvements in artificial intelligence (AI) is healthcare.…
Generative models, such as GPT-2, have demonstrated impressive results recently. A fundamental question we'd like to address is: where did the generated text come from? This work is our initial effort toward answering the question by using…
Purpose: Our study presents an enhanced approach to medical image caption generation by integrating concept detection into attention mechanisms. Method: This method utilizes sophisticated models to identify critical concepts within medical…
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…