Search Results for author:
Found 21 papers, 16 papers with code
Learning to Rank in the Age of Muppets: Effectiveness–Efficiency Tradeoffs in Multi-Stage Ranking
It is well known that rerankers built on pretrained transformer models such as BERT have dramatically improved retrieval effectiveness in many tasks.
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
Traditional methods for reasoning segmentation rely on supervised fine-tuning with categorical labels and simple descriptions, limiting its out-of-domain generalization and lacking explicit reasoning processes.
Improving Similar Case Retrieval Ranking Performance By Revisiting RankSVM
In our paper, however, we try to improve the ranking performance of current models from the perspective of learning to rank instead of language models.
SVFR: A Unified Framework for Generalized Video Face Restoration
In this paper, we propose a novel approach for the Generalized Video Face Restoration (GVFR) task, which integrates video BFR, inpainting, and colorization tasks that we empirically show to benefit each other.
Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval
We further enhance the use of harder-negatives in model training, and benchmark a variety of video-text models on RTime.
Lyra: An Efficient and Speech-Centric Framework for Omni-Cognition
As Multi-modal Large Language Models (MLLMs) evolve, expanding beyond single-domain capabilities is essential to meet the demands for more versatile and efficient AI.
Ranked #1 on
Visual Question Answering (VQA)
on EgoSchema
Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection
To exploit this bias in Judge LLMs, we introduce the Emoji Attack -- a method that places emojis within tokens to increase the embedding differences between sub-tokens and their originals.
SCOPE: Sign Language Contextual Processing with Embedding from LLMs
Current methods in vision-based sign language recognition (SLR) and translation (SLT) struggle with dialogue scenes due to limited dataset diversity and the neglect of contextually relevant information.
Toward Open-Set Human Object Interaction Detection
To address this challenge, we introduce a simple Disentangled HOI Detection (DHD) model for detecting novel relationships by integrating an open-set object detector with a Visual Language Model (VLM).
Computational Modelling of Plurality and Definiteness in Chinese Noun Phrases
In this paper, we focus on the omission of the plurality and definiteness markers in Chinese noun phrases (NPs) to investigate the predictability of their intended meaning given the contexts.
Taiyi: A Bilingual Fine-Tuned Large Language Model for Diverse Biomedical Tasks
The case study involving additional biomedical NLP tasks further shows Taiyi's considerable potential for bilingual biomedical multi-tasking.
Structure Aggregation for Cross-Spectral Stereo Image Guided Denoising
Instead of aligning the input images via conventional stereo matching, we aggregate structures from the guidance image to estimate a clean structure map for the noisy target image, which is then used to regress the final denoising result with a spatially variant linear representation model.
TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval
In this paper, we propose Token Shift and Selection Network (TS2-Net), a novel token shift and selection transformer architecture, which dynamically adjusts the token sequence and selects informative tokens in both temporal and spatial dimensions from input video samples.
Ranked #9 on
Video Retrieval
on MSR-VTT-1kA
An Efficient End-to-End 3D Voxel Reconstruction based on Neural Architecture Search
However, many previous works employ neural networks with fixed architecture and size to represent different 3D objects, which lead to excessive network parameters for simple objects and limited reconstruction accuracy for complex objects.
Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic
In this paper, we formulate a multi-task safe reinforcement learning with social attention to improve the safety and efficiency when interacting with other traffic participants.
High-fidelity 3D Model Compression based on Key Spheres
Compared to previous works, our method achieves the high-fidelity and high-compression 3D object coding and reconstruction.
Deep Learning Assisted End-to-End Synthesis of mm-Wave Passive Networks with 3D EM Structures: A Study on A Transformer-Based Matching Network
This paper presents a deep learning assisted synthesis approach for direct end-to-end generation of RF/mm-wave passive matching network with 3D EM structures.
Improving the Accuracy of Learning Example Weights for Imbalance Classification
To solve the imbalance classification, methods of weighting examples haven been proposed.
A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios
The test benchmark and baselines are to provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing the progress of RL-based methods for intersection autonomous driving control.
SN-Graph: a Minimalist 3D Object Representation for Classification
Using deep learning techniques to process 3D objects has achieved many successes.
Spherical Transformer: Adapting Spherical Signal to CNNs
To this end, the proposed method first uses local structured sampling methods such as HEALPix to construct a transformer grid by using the information of spherical points and its adjacent points, and then transforms the spherical signals to the vectors through the grid.
