相关论文: Enhancing DETRs Variants through Improved Content …
Inability of the naive users to formulate appropriate queries is a fundamental problem in web search engines. Therefore, assisting users to issue more effective queries is an important way to improve users' happiness. One effective approach…
Video moment retrieval (MR) and highlight detection (HD) based on natural language queries are two highly related tasks, which aim to obtain relevant moments within videos and highlight scores of each video clip. Recently, several methods…
Parameter efficient fine tuning methods like LoRA have enabled task specific adaptation of large language models, but efficiently composing multiple specialized adapters for unseen tasks remains challenging. We present a novel framework for…
While the self-attention mechanism has been widely used in a wide variety of tasks, it has the unfortunate property of a quadratic cost with respect to the input length, which makes it difficult to deal with long inputs. In this paper, we…
Query auto-completion (QAC) plays a crucial role in modern search systems. However, in real-world applications, there are two pressing challenges that still need to be addressed. First, there is a need for hierarchical personalized…
Recent DETR-based methods have advanced the development of Video Instance Segmentation (VIS) through transformers' efficiency and capability in modeling spatial and temporal information. Despite harvesting remarkable progress, existing…
Existing techniques for text detection can be broadly classified into two primary groups: segmentation-based and regression-based methods. Segmentation models offer enhanced robustness to font variations but require intricate…
While entity-oriented neural IR models have advanced significantly, they often overlook a key nuance: the varying degrees of influence individual entities within a document have on its overall relevance. Addressing this gap, we present…
In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from…
Dense depth completion is essential for autonomous systems and 3D reconstruction. In this paper, a lightweight yet efficient network (S\&CNet) is proposed to obtain a good trade-off between efficiency and accuracy for the dense depth…
Most existing audio-text retrieval (ATR) approaches typically rely on a single-level interaction to associate audio and text, limiting their ability to align different modalities and leading to suboptimal matches. In this work, we present a…
Retrieval-Augmented Code Generation (RACG) is a critical technique for enhancing code generation by retrieving relevant information. In this work, we conduct an in-depth analysis of code retrieval by systematically masking specific features…
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training…
Despite the recent progress made in Video Question-Answering (VideoQA), these methods typically function as black-boxes, making it difficult to understand their reasoning processes and perform consistent compositional reasoning. To address…
Text-to-Video Retrieval (TVR) is essential in video platforms. Dense retrieval with dual-modality encoders leads in accuracy, but its computation and storage scale poorly with corpus size. Thus, real-time large-scale applications adopt…
In this work we leverage recent advances in context-sensitive language models to improve the task of query expansion. Contextualized word representation models, such as ELMo and BERT, are rapidly replacing static embedding models. We…
We present APQ for efficient deep learning inference on resource-constrained hardware. Unlike previous methods that separately search the neural architecture, pruning policy, and quantization policy, we optimize them in a joint manner. To…
A major difficulty in applying word vector embeddings in IR is in devising an effective and efficient strategy for obtaining representations of compound units of text, such as whole documents, (in comparison to the atomic words), for the…
Leveraging vast and continually updated knowledge from the Internet has been considered an important ability for a dialogue system. Therefore, the dialogue query generation task is proposed for generating search queries from dialogue…
Query rewriting is pivotal for enhancing dense retrieval, yet current methods demand large-scale supervised data or suffer from inefficient reinforcement learning (RL) exploration. In this work, we first establish that guiding Large…