130 citations · 359 across the 19 of their papers we have counts for
21 papers
VideoGLUE: Video General Understanding Evaluation of Foundation Models
Liangzhe Yuan, Nitesh Bharadwaj Gundavarapu, Long Zhao +14
We evaluate the video understanding capabilities of existing foundation models (FMs) using a carefully designed experiment protocol consisting of three hallmark tasks (action recog…
Emergent Correspondence from Image Diffusion
Luming Tang, Menglin Jia, Qianqian Wang +2
Finding correspondences between images is a fundamental problem in computer vision. In this paper, we show that correspondence emerges in image diffusion models without any explici…
Search for astrophysical electron antineutrinos in Super-Kamiokande with 0.01wt% gadolinium-loaded water
M. Harada, K. Abe, C. Bronner +238
We report the first search result for the flux of astrophysical electron antineutrinos for energies O(10) MeV in the gadolinium-loaded Super-Kamiokande (SK) detector. In June 2020,…
PromptFusion: Decoupling Stability and Plasticity for Continual Learning
Haoran Chen, Zuxuan Wu, Xintong Han +2
Current research on continual learning mainly focuses on relieving catastrophic forgetting, and most of their success is at the cost of limiting the performance of newly incoming t…
Measurement of the cosmogenic neutron yield in Super-Kamiokande with gadolinium loaded water
Kamiokande Collaboration, M. Shinoki, K. Abe +238
Cosmic-ray muons that enter the Super-Kamiokande detector cause hadronic showers due to spallation in water, producing neutrons and radioactive isotopes. Those are a major backgrou…
Searching for neutrinos from solar flares across solar cycles 23 and 24 with the Super-Kamiokande detector
K. Okamoto, K. Abe, Y. Hayato +242
Neutrinos associated with solar flares (solar-flare neutrinos) provide information on particle acceleration mechanisms during the impulsive phase of solar flares. We searched using…
Search for Cosmic-ray Boosted Sub-GeV Dark Matter using Recoil Protons at Super-Kamiokande
Kamiokande Collaboration, K. Abe, Y. Hayato +218
We report a search for cosmic-ray boosted dark matter with protons using the 0.37 megatonyears data collected at Super-Kamiokande experiment during the 1996-2018 period (SK…
Searching for Structure in Unfalsifiable Claims
Peter Ebert Christensen, Frederik Warburg, Menglin Jia +1
Social media platforms give rise to an abundance of posts and comments on every topic imaginable. Many of these posts express opinions on various aspects of society, but their unfa…
Search for supernova bursts in Super-Kamiokande IV
Kamiokande collaboration, M. Mori, K. Abe +242
Super-Kamiokande has been searching for neutrino bursts characteristic of core-collapse supernovae continuously, in real time, since the start of operations in 1996. The present wo…
Pre-Supernova Alert System for Super-Kamiokande
Kamiokande Collaboration, L. N. Machado, K. Abe +223
In 2020, the Super-Kamiokande (SK) experiment moved to a new stage (SK-Gd) in which gadolinium (Gd) sulfate octahydrate was added to the water in the detector, enhancing the effici…
Testing Non-Standard Interactions Between Solar Neutrinos and Quarks with Super-Kamiokande
Kamiokande Collaboration, P. Weatherly, K. Abe +268
Non-Standard Interactions (NSI) between neutrinos and matter affect the neutrino flavor oscillations. Due to the high matter density in the core of the Sun, solar neutrinos are sui…
Visual Prompt Tuning
Menglin Jia, Luming Tang, Bor-Chun Chen +4
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) as a…
Rethinking Nearest Neighbors for Visual Classification
Menglin Jia, Bor-Chun Chen, Zuxuan Wu +3
Neural network classifiers have become the de-facto choice for current "pre-train then fine-tune" paradigms of visual classification. In this paper, we investigate k-Nearest-Neighb…
When in Doubt: Improving Classification Performance with Alternating Normalization
Menglin Jia, Austin Reiter, Ser-Nam Lim +2
We introduce Classification with Alternating Normalization (CAN), a non-parametric post-processing step for classification. CAN improves classification accuracy for challenging exa…
Exploring Visual Engagement Signals for Representation Learning
Menglin Jia, Zuxuan Wu, Austin Reiter +3
Visual engagement in social media platforms comprises interactions with photo posts including comments, shares, and likes. In this paper, we leverage such visual engagement clues a…
Intentonomy: a Dataset and Study towards Human Intent Understanding
Menglin Jia, Zuxuan Wu, Austin Reiter +3
An image is worth a thousand words, conveying information that goes beyond the physical visual content therein. In this paper, we study the intent behind social media images with a…
Learning Occupancy Function from Point Clouds for Surface Reconstruction
Meng Jia, Matthew Kyan
Implicit function based surface reconstruction has been studied for a long time to recover 3D shapes from point clouds sampled from surfaces. Recently, Signed Distance Functions (S…
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
Menglin Jia, Mengyun Shi, Mikhail Sirotenko +5
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-graine…
Deep Multi-Modal Sets
Austin Reiter, Menglin Jia, Pu Yang +1
Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning…
Class-Balanced Loss Based on Effective Number of Samples
Yin Cui, Menglin Jia, Tsung-Yi Lin +2
With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of th…
A Deep-Learning-Based Fashion Attributes Detection Model
Menglin Jia, Yichen Zhou, Mengyun Shi +1
Analyzing fashion attributes is essential in the fashion design process. Current fashion forecasting firms, such as WGSN utilizes information from all around the world (from fashio…