Related papers: ListT5: Listwise Reranking with Fusion-in-Decoder …
Search systems often employ a re-ranking pipeline, wherein documents (or passages) from an initial pool of candidates are assigned new ranking scores. The process enables the use of highly-effective but expensive scoring functions that are…
Passage reranking is a critical task in various applications, particularly when dealing with large volumes of documents. Existing neural architectures have limitations in retrieving the most relevant passage for a given question because the…
BERT-based information retrieval models are expensive, in both time (query latency) and computational resources (energy, hardware cost), making many of these models impractical especially under resource constraints. The reliance on a query…
This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search. Built on [1], a directed image graph robust to outlier distraction is proposed. In our approach, the relevance among images is encoded in the…
Retrieve-and-rerank is a prevalent framework in neural information retrieval, wherein a bi-encoder network initially retrieves a pre-defined number of candidates (e.g., K=100), which are then reranked by a more powerful cross-encoder model.…
Transformer-based models like BERT excel at short text classification but struggle with long document classification (LDC) due to input length limitations and computational inefficiencies. In this work, we propose an efficient, zero-shot…
Modern recommendation and search systems typically employ multi-stage ranking architectures to efficiently handle billions of candidates. The conventional approach uses distinct L1 (candidate retrieval) and L2 (re-ranking) models with…
Zero-shot action recognition is the task of recognizingaction classes without visual examples, only with a seman-tic embedding which relates unseen to seen classes. Theproblem can be seen as learning a function which general-izes well to…
In various natural language processing tasks, passage retrieval and passage re-ranking are two key procedures in finding and ranking relevant information. Since both the two procedures contribute to the final performance, it is important to…
Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids), thereby enabling end-to-end optimization and seamless integration with generative language models (LMs).…
Person Re-ID has been gaining a lot of attention and nowadays is of fundamental importance in many camera surveillance applications. The task consists of identifying individuals across multiple cameras that have no overlapping views. Most…
Time series foundation models (TSFMs) have recently achieved strong zero-shot forecasting performance through large-scale pretraining and retrieval-augmented prediction. However, our empirical analysis reveals a non-trivial limitation of…
Large Language Models (LLMs) have emerged as powerful tools for passage reranking in information retrieval, leveraging their superior reasoning capabilities to address the limitations of conventional models on complex queries. However,…
Modern retrieval systems do not rely on a single ranking model to construct their rankings. Instead, they generally take a cascading approach where a sequence of ranking models are applied in multiple re-ranking stages. Thereby, they…
Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search…
Zero-Shot Composed Image Retrieval (ZS-CIR) aims to retrieve target images given a multimodal query (comprising a reference image and a modification text), without training on annotated triplets. Existing methods typically convert the…
Long-Term tracking is a hot topic in Computer Vision. In this context, competitive models are presented every year, showing a constant growth rate in performances, mainly measured in standardized protocols as Visual Object Tracking (VOT)…
Ranked list truncation is of critical importance in a variety of professional information retrieval applications such as patent search or legal search. The goal is to dynamically determine the number of returned documents according to some…
Zero-shot Composed Image Retrieval (ZS-CIR) aims to retrieve a target image given a reference image and a relative text, without relying on costly triplet annotations. Existing CLIP-based methods face two core challenges: (1) union-based…
Image retrieval remains a fundamental yet challenging problem in computer vision. While recent advances in Multimodal Large Language Models (MLLMs) have demonstrated strong reasoning capabilities, existing methods typically employ them only…