Institution
Salesforce.com
About: Salesforce.com is a based out in . It is known for research contribution in the topics: User interface & Object (computer science). The organization has 2418 authors who have published 2775 publications receiving 63956 citations.
Topics: User interface, Object (computer science), Metadata, Cloud computing, Set (abstract data type)
Papers published on a yearly basis
Papers
More filters
••
01 Jan 2018TL;DR: This work presents the prototype of IoT-based Real Time smart street Parking System (IoT-based RTSSPS) with accessibility of data to make it simpler for residents and drivers to locate a free parking slot at the streets.
Abstract: Smart city is a vision that aims to integrate multiple information and communication solutions to residents with essential services like smart parking inside the all streets. Today, the parking systems has been changed by new advances that are empowering urban communities to diminish levels of congestions altogether. Internet of Things (IoT) is also new advancement which helps in detection of vehicle occupancy and congestion by basic intelligence and computational capability to make a smart parking system. The main motivation of using IoT for parking is to collect the data easily for free parking slots. This work presents the prototype of IoT-based Real Time smart street Parking System (IoT-based RTSSPS) with accessibility of data to make it simpler for residents and drivers to locate a free parking slot at the streets. Firstly, this work presents the introduction of IoT for smart parking with technology backgrounds, challenges of accessing IoT and database. Secondly, this work presents the prototype design of IoT-based RTSSPS with architecture and algorithm. IoT-based RTSSPS architecture is divided into three parts IoT-based WSN centric smart street parking module, IoT-based data centric smart street parking module and IoT-based cloud centric smart street parking module with street parking algorithm, evaluation and future directions.
14 citations
••
11 Jul 2021TL;DR: The authors proposed an interactive observation-based model (IOBM) to estimate the observation probability, which uses the embedding as a proxy confounder to uncover the relevant information for the prediction of the observation propensity.
Abstract: Counterfactual Learning to Rank (CLTR) becomes an attractive research topic due to its capability of training ranker with click logs. However, CLTR inherently suffers from a large amount of bias caused by confounders, variables that affect both the observation (examination) behavior and click behavior. Recent efforts to correct bias mostly focus on position bias, which assumes that each observation in a ranking list is isolated and only depends on the position. Though effective, users often engage with documents in an interactive manner. Ignoring the interactions between observations/clicks would incur a large interactional observation bias no matter how much data is collected. In this work, we leverage the embedding method to develop an Interactional Observation-Based Model (IOBM) to estimate the observation probability. We argue that while there exist complex observed and unobserved confounders for observation/click interactions, it is sufficient to use the embedding as a proxy confounder to uncover the relevant information for the prediction of the observation propensity. Moreover, the embedding could offer an alternative to the fully specified generative model for observation and decouples the complex interaction structure of observations/clicks. In our IOBM, we first learn the individual observation embedding to capture position and click information. Then, we learn the interactional observation embedding to uncover their local interaction structure. To filter out irrelevant information and reduce contextual bias, we utilize query context information and propose the intra-observation attention and the inter-observation attention, respectively. We conduct extensive experiments on two LTR benchmark datasets, demonstrating that the proposed IOBM consistently achieves better performance over the baseline models in various click situations and verifying its effectiveness of eliminating interactional observation bias.
14 citations
•
04 Aug 2010TL;DR: In this paper, the search term includes a plurality of words, and the search query is then modified to include the first combination in a logical OR relationship with the synonyms of the first word and the second combination in an logical OR relation with the second word.
Abstract: Systems and methods for performing a data search through a search query is disclosed. The method includes receiving the search query and parsing the search query to retrieve a search term. The search term includes a plurality of words. In the search term, a first combination of two or more of the plurality of words and a second combination of two or more of the plurality of words are indentified. The first combination and the second combination include a common term. The first combination ends with the common term and the second combination begins with the common term. The method further includes retrieving synonyms for the first combination and the second combination exist in a synonym storage and the search query is then modified to include the first combination in a logical OR relationship with the synonyms of the first combination and the second combination in a logical OR relationship with the synonyms of the second combination. The modified search query is executed against a data store.
14 citations
•
TL;DR: This report investigates the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS dataset, and finds a major cause is the inaccurate classification of object proposals.
Abstract: Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balanced and class-limited benchmarks, such as Microsoft COCO dataset [8]. In this report, we investigate the performance drop phenomenon of state-of-the-art two-stage instance segmentation models when processing extreme long-tail training data based on the LVIS [5] dataset, and find a major cause is the inaccurate classification of object proposals. Based on this observation, we propose to calibrate the prediction of classification head to improve recognition performance for the tail classes. Without much additional cost and modification of the detection model architecture, our calibration method improves the performance of the baseline by a large margin on the tail classes. Codes will be available. Importantly, after the submission, we find significant improvement can be further achieved by modifying the calibration head, which we will update later.
14 citations
•
18 Jul 2008TL;DR: In this paper, the authors provided mechanisms and methods for generating a custom report using an on-demand database service, which can enable generating reports that reflect a relationship between at least two different objects.
Abstract: In accordance with embodiments, there are provided mechanisms and methods for generating a custom report using an on-demand database service. These mechanisms and methods for generating an on-demand database service custom report can enable embodiments to generate reports that reflect a relationship between at least two different objects. The ability of embodiments to provide such additional insight into database contents may lead to more efficient and effective reporting.
14 citations
Authors
Showing all 2418 results
Name | H-index | Papers | Citations |
---|---|---|---|
Philip S. Yu | 148 | 1914 | 107374 |
Michael R. Lyu | 89 | 696 | 33257 |
Silvio Savarese | 89 | 386 | 35975 |
Jiashi Feng | 77 | 426 | 21521 |
Richard Socher | 77 | 274 | 97703 |
Haibin Ling | 72 | 383 | 20858 |
Dragomir R. Radev | 69 | 288 | 20131 |
Irwin King | 67 | 476 | 19056 |
Steven C. H. Hoi | 66 | 375 | 15935 |
Xiaodan Liang | 61 | 318 | 14121 |
Caiming Xiong | 60 | 336 | 18037 |
Min-Yen Kan | 52 | 253 | 10207 |
Justin Yifu Lin | 48 | 302 | 13491 |
Hannaneh Hajishirzi | 42 | 181 | 7802 |
Larry S. Davis | 40 | 105 | 6960 |