Always private
DuckDuckGo never tracks your searches.
Learn More
You can hide this reminder in Search Settings
All regions
Argentina
Australia
Austria
Belgium (fr)
Belgium (nl)
Brazil
Bulgaria
Canada (en)
Canada (fr)
Catalonia
Chile
China
Colombia
Croatia
Czech Republic
Denmark
Estonia
Finland
France
Germany
Greece
Hong Kong
Hungary
Iceland
India (en)
Indonesia (en)
Ireland
Israel (en)
Italy
Japan
Korea
Latvia
Lithuania
Malaysia (en)
Mexico
Netherlands
New Zealand
Norway
Pakistan (en)
Peru
Philippines (en)
Poland
Portugal
Romania
Russia
Saudi Arabia
Singapore
Slovakia
Slovenia
South Africa
Spain (ca)
Spain (es)
Sweden
Switzerland (de)
Switzerland (fr)
Taiwan
Thailand (en)
Turkey
Ukraine
United Kingdom
US (English)
US (Spanish)
Vietnam (en)
Safe search: moderate
Strict
Moderate
Off
Any time
Any time
Past day
Past week
Past month
Past year
  1. Only showing results from arxiv.org

    Clear filter to show all search results

  2. propose a new benchmark dataset for Evaluating Localization of Social Activities (ELSA) in urban street images. ELSA draws on theoretical frameworks in urban sociology and design. While majority of action recognition datasets are collected in controlled settings, we use in-the-wild street-level imagery, where the size of
  3. et al. [10] introduced JRDB-Act, a video dataset for group-based social activities in university campus scenes. In con-trast, ELSA focuses on the more challenging task of local-izing social activities in images, where models must infer activities from a snapshot without the temporal cues avail-able in videos. 3. ELSA: A Benchmark for Evaluating ...
  4. Jun 3, 2024In response to these challenges, we propose ELSA, a new benchmark dataset for Evaluating Localization of Social Activities in Urban Streets, using closed as well as open-vocabulary object detection models in recognizing and localizing human activity in urban streets from still images. We employ a multi-labeling scheme and define 34 unique ...
  5. Oct 31, 2024In machine learning research, it is common to evaluate algorithms via their performance on standard benchmark datasets. While a growing body of work establishes guidelines for -- and levies criticisms at -- data and benchmarking practices in machine learning, comparatively less attention has been paid to the data repositories where these datasets are stored, documented, and shared. In this ...
  6. Oct 31, 2024Abstract. In machine learning research, it is common to evaluate algorithms via their performance on standard benchmark datasets. While a growing body of work establishes guidelines for—and levies criticisms at—data and benchmarking practices in machine learning, comparatively less attention has been paid to the data repositories where these datasets are stored, documented, and shared.
  7. Oct 14, 2024Time series analysis has become increasingly important in various domains, and developing effective models relies heavily on high-quality benchmark datasets. Inspired by the success of Natural Language Processing (NLP) benchmark datasets in advancing pre-trained models, we propose a new approach to create a comprehensive benchmark dataset for time series analysis. This paper explores the ...
  8. We evaluate the performance of ELSA on a benchmark Amazon review dataset that has been used in various cross-lingual sentiment classification studies [50, 58, 62]. The benchmark dataset covers nine tasks combined from three target languages (i.e., Japanese, French, and German) and three domains (i.e., book, DVD, and mu-sic).
  9. Dec 17, 20243) Dynamic. The domains and languages covered by AIR-Bench are constantly augmented to provide an increasingly comprehensive evaluation benchmark for community developers. We develop a reliable and robust data generation pipeline to automatically create diverse and high-quality evaluation datasets based on real-world corpora.
  10. •Our model, Elsa, achieves the best or comparable de-tection performance over multiple benchmark datasets, despite leveraging only a small set of labeled samples. • Elsa is robust to challenging settings, where the train-ing set contains unknown anomalies (Scenario-2 in experiments). Such property is important in real-world environments. 2.
  11. datasets that are based on the Norwegian Review Corpus - NoReC (Velldal et al.,2018) - fits this bill. While Section3.2describes how we build on NoReC to create an exploratory dataset for ELSA, we first describe the different levels of existing an-notations in NoReC below. 3.1 NoReC NoReC is a multi-domain dataset of full-text pro-

    Can’t find what you’re looking for?

    Help us improve DuckDuckGo searches with your feedback

Custom date rangeX