Filters








97 Hits in 5.0 sec

Gaussian process decentralized data fusion meets transfer learning in large-scale distributed cooperative perception

Ruofei Ouyang, Bryan Kian Hsiang Low
<span title="2019-01-28">2019</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jmjdfeig5rayzgfuauvumileza" style="color: black;">Autonomous Robots</a> </i> &nbsp;
a Formal Definition of Moral Responsibility and Intention Joseph Halpern*, Max Kleiman-Weiner Towards a Neural Conversation Model with Diversity Net Using Determinantal Point Processes Yiping Song*, Rui  ...  Deng Dynamic Determinantal Point Processes Takayuki Osogami*, Rudy Raymond, Akshay Goel, Tomoyuki Shirai, Takanori Maehara Dynamic Network Embedding by Modeling Triadic Closure Process Lekui Zhou, Yang  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10514-018-09826-z">doi:10.1007/s10514-018-09826-z</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/67yqhwmgozccxni56rxmuapjgm">fatcat:67yqhwmgozccxni56rxmuapjgm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319033824/https://aaai.org/Conferences/AAAI-18/wp-content/uploads/2017/12/AAAI-18-Accepted-Paper-List.Web_.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a3/9b/a39b2e42983c9863a5e6ebaad48c6bce360da7f3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10514-018-09826-z"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Towards Diverse and Accurate Image Captions via Reinforcing Determinantal Point Process [article]

Qingzhong Wang, Antoni B. Chan
<span title="2019-08-14">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we combine determinantal point process (DPP) and reinforcement learning (RL) and propose a novel reinforcing DPP (R-DPP) approach to generate a set of captions with high quality and diversity  ...  We show that R-DPP performs better on accuracy and diversity than using noise as a control signal (GANs, VAEs). Moreover, R-DPP is able to preserve the modes of the learned distribution.  ...  Determinantal point process (DPP).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.04919v1">arXiv:1908.04919v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5uvoc2im65gxfisc3qg6s5p6n4">fatcat:5uvoc2im65gxfisc3qg6s5p6n4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930160541/https://arxiv.org/pdf/1908.04919v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/58/a7/58a77455b1c38afe1eab4bec664bd866eba1573d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1908.04919v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep learning for spatio-temporal forecasting – application to solar energy [article]

Vincent Le Guen
<span title="2022-05-07">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We address both the deterministic context with the proposed DILATE loss function and the probabilistic context with the STRIPE model.  ...  Our second direction is to augment incomplete physical models with deep data-driven networks for accurate forecasting.  ...  Remerciements Je tiens à remercier ici toutes les personnes qui ont concouru à l'achèvement du travail présenté dans ce manuscrit.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.03571v1">arXiv:2205.03571v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dwkprkwf6ncgjcnvkpx3yrdfjm">fatcat:dwkprkwf6ncgjcnvkpx3yrdfjm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220511203748/https://arxiv.org/pdf/2205.03571v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/90/84/9084939639c6aeaca6e6708f63517d08b3001cc8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.03571v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Toward Interpretability of Dual-Encoder Models for Dialogue Response Suggestions [article]

Yitong Li, Dianqi Li, Sushant Prakash, Peng Wang
<span title="2020-03-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This can help not only with model interpretability, but can also further improve model accuracy. We propose an approximation method that uses a neural network to calculate the mutual information.  ...  This work shows how to improve and interpret the commonly used dual encoder model for response suggestion in dialogue.  ...  [29] uses Determinantal Point Processes to generate responses with diversity and ground knowledge can also be utilized to generate novel results [8] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.04998v1">arXiv:2003.04998v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/krbawitty5aslfrfo3kvtukgvi">fatcat:krbawitty5aslfrfo3kvtukgvi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320193431/https://arxiv.org/pdf/2003.04998v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.04998v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Generative Models in Engineering Design: A Review [article]

Lyle Regenwetter, Amin Heyrani Nobari, Faez Ahmed
<span title="2022-03-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We present a review and analysis of Deep Generative Machine Learning models in engineering design.  ...  We structure our review as an exposition of the algorithms, datasets, representation methods, and applications commonly used in the current literature.  ...  PaDGAN expands on the conventional GAN architecture by modeling design performance and design diversity using a Determinantal Point Process (DPP) kernel [136] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.10863v4">arXiv:2110.10863v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zc4mo4nwzjdlne5jbvaetyugxy">fatcat:zc4mo4nwzjdlne5jbvaetyugxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220210075431/https://arxiv.org/pdf/2110.10863v3.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/dd/b7/ddb7ab44358387354e7244055d01fb02e5563360.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.10863v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Pruning and Quantization for Deep Neural Network Acceleration: A Survey [article]

Tailin Liang, John Glossner, Lei Wang, Shaobo Shi, Xiaotong Zhang
<span title="2021-06-15">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Network compression can often be realized with little loss of accuracy. In some cases accuracy may even improve.  ...  Both pruning and quantization can be used independently or combined.  ...  Open Neural Network Exchange (ONNX) [190] is an open-source tool to parse AI models written for a variety diverse frameworks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.09671v3">arXiv:2101.09671v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a34q7ca24zbylmjrddlkt3ggai">fatcat:a34q7ca24zbylmjrddlkt3ggai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210617014800/https://arxiv.org/pdf/2101.09671v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f4/db/f4db23b63b7ccd1ada4ac000bac4d1eb9711617d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.09671v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarization [article]

Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev
<span title="2021-04-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In order to satisfy the needs of different types of users, we define a new query-based multi-domain meeting summarization task, where models have to select and summarize relevant spans of meetings in response  ...  to a query, and we introduce QMSum, a new benchmark for this task.  ...  ., PM) to denote speakers, and use the full name like 'Project Manager' instead. Abbreviations. In the raw meeting transcripts, some of abbreviations are along with character '_'.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.05938v1">arXiv:2104.05938v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/24p3u2nimrei7mwnwr32ouk2qq">fatcat:24p3u2nimrei7mwnwr32ouk2qq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210416105245/https://arxiv.org/pdf/2104.05938v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/aa/28/aa28873534c24e4a8c5deb7bff723cd5fc69a6f0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.05938v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Video Summarization Using Deep Neural Networks: A Survey [article]

Evlampios Apostolidis, Eleni Adamantidou, Alexandros I. Metsai, Vasileios Mezaris, Ioannis Patras
<span title="2021-09-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Several approaches have been developed over the last couple of decades and the current state of the art is represented by methods that rely on modern deep neural network architectures.  ...  Then, we suggest a taxonomy of the existing algorithms and provide a systematic review of the relevant literature that shows the evolution of the deep-learning-based video summarization technologies and  ...  ) the SUM-GAN method and its extension that uses the Determinantal Point Process to increase the diversity of the summary content (called SUM-GAN dpp ) perform worse than a random summarizer.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.06072v2">arXiv:2101.06072v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7mozntfhdrf3lkw6pwcr5v2rpu">fatcat:7mozntfhdrf3lkw6pwcr5v2rpu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210930062959/https://arxiv.org/pdf/2101.06072v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/40/ff/40ffdf58932db8284a33a56b6ce8bded2f5a829b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2101.06072v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Determinantal Point Processes for Machine Learning

Alex Kulesza
<span title="">2012</span> <i title="Now Publishers"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ka2h7lkphrfvjlabybgqbnn2jq" style="color: black;">Foundations and Trends® in Machine Learning</a> </i> &nbsp;
Determinantal point processes (DPPs) are elegant probabilistic models of repulsion that arise in quantum physics and random matrix theory.  ...  applications like finding diverse sets of high-quality search results, building informative summaries by selecting diverse sentences from documents, modeling non-overlapping human poses in images or video  ...  This subset is distributed as a determinantal point process.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1561/2200000044">doi:10.1561/2200000044</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qqq2fvo6tfcnbd73ee2oa43num">fatcat:qqq2fvo6tfcnbd73ee2oa43num</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170811010738/http://www.alexkulesza.com/pubs/dpps_fnt12.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1561/2200000044"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

An analytical study of information extraction from unstructured and multidimensional big data

Kiran Adnan, Rehan Akbar
<span title="2019-10-17">2019</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pkhnkszyprhb3orbf6g7tqmgiu" style="color: black;">Journal of Big Data</a> </i> &nbsp;
IBM estimated that more than 2.5 quintillion bytes of data are generated every Abstract Process of information extraction (IE) is used to extract useful information from unstructured or semi-structured  ...  Introduction Information extraction (IE) process extracts useful structured information from the unstructured data in the form of entities, relations, objects, events and many other types.  ...  ; BFM: Bayesian fusion model; CNN: convolutional neural network; CRF: conditional random forest; CS: code switching; DBN: deep belief network; DL: deep learning; DPP: determinantal point process; DTW:  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s40537-019-0254-8">doi:10.1186/s40537-019-0254-8</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qy5l55um7feeblec4hxohr3pqa">fatcat:qy5l55um7feeblec4hxohr3pqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212225913/https://journalofbigdata.springeropen.com/track/pdf/10.1186/s40537-019-0254-8" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f5/bd/f5bdf3359216640bbe1e8ed4c723fcd429caf58f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s40537-019-0254-8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Unified Simulation, Perception, and Generation of Human Behavior [article]

Ye Yuan
<span title="2022-04-28">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this thesis, we take a holistic approach to human behavior modeling and tackle its three essential aspects -- simulation, perception, and generation.  ...  We also discuss the lessons learned and our vision for what is next for human behavior modeling.  ...  To this end, we make use of determinantal point processes (DPPs) to model the diversity within a set.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13678v1">arXiv:2204.13678v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ls2kmgifbjbaffgwodgdiilstm">fatcat:ls2kmgifbjbaffgwodgdiilstm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220504192432/https://arxiv.org/pdf/2204.13678v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/92/c4/92c42bc24f4719b70271aa4a4ef887697c2545d5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.13678v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction [article]

Balakrishnan Varadarajan, Ahmed Hefny, Avikalp Srivastava, Khaled S. Refaat, Nigamaa Nayakanti, Andre Cornman, Kan Chen, Bertrand Douillard, Chi Pang Lam, Dragomir Anguelov, Benjamin Sapp
<span title="2021-12-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we present MultiPath++, a future prediction model that achieves state-of-the-art performance on popular benchmarks.  ...  Second, we reconsider the choice of pre-defined, static anchors, and develop a way to learn latent anchor embeddings end-to-end in the model.  ...  Diverse trajectory forecasting with determinantal point processes. ICLR, 2020. [51] Manzil Zaheer, Satwik Kottur, Siamak Ravanbakhsh, Barnabas Poczos, Russ R Salakhutdinov, and Alexander J Smola.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14973v3">arXiv:2111.14973v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jyrdrlpsyncxhlpihh37jppjzm">fatcat:jyrdrlpsyncxhlpihh37jppjzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211231103412/https://arxiv.org/pdf/2111.14973v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8b/16/8b1602a911eb0f1753f22429952379a35c276a0f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2111.14973v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Molecular Characterization of Brain and other Structures in Vertebrates and Invertebrates

Luisetto M
<span title="2019-05-07">2019</span> <i title="Iris Publishers LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e2rw2nmh65ahvepgmr5qtahhgi" style="color: black;">Archives in Neurology &amp; Neuroscience</a> </i> &nbsp;
A wide scope of invertebrate immunocytes share with vertebrate phagocytic macrophages, phagocytosis, chemotaxis, tumorocidal activity and cytotoxic natural killer (NK) cells, and cytotoxicity in stress  ...  The process start when the immune-cells (macrophages) release the soluble factors that stimulate the fibroblasts population.  ...  this process in some metazoaor in determinante stage of their life (in examples adults vs embryo).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33552/ann.2019.03.000572">doi:10.33552/ann.2019.03.000572</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ofxaonqwmfawjgdj77c2p6ivwq">fatcat:ofxaonqwmfawjgdj77c2p6ivwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200319222634/https://irispublishers.com/ann/pdf/ANN.MS.ID.000572.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/1f/10/1f1069420008a9d05294fb9128716520710f8fdf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.33552/ann.2019.03.000572"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Transcript to Video: Efficient Clip Sequencing from Texts [article]

Yu Xiong, Fabian Caba Heilbron, Dahua Lin
<span title="2021-07-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Specifically, we propose a Content Retrieval Module and a Temporal Coherent Module to learn visual-language representations and model shot sequencing styles, respectively.  ...  To meet the demands for non-experts, we present Transcript-to-Video -- a weakly-supervised framework that uses texts as input to automatically create video sequences from an extensive collection of shots  ...  How local is the local diversity? reinforcing sequen- tial determinantal point processes with dynamic ground sets for supervised video summarization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.11851v1">arXiv:2107.11851v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vfcx7w75kzgg7ppurgswceoi5i">fatcat:vfcx7w75kzgg7ppurgswceoi5i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210730175708/https://arxiv.org/pdf/2107.11851v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/41/68/4168090077a0a8947f68fe2e127aac38fafc58ba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.11851v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

The State of AI Ethics Report (June 2020) [article]

Abhishek Gupta
<span title="2020-06-25">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It has never been more important that we keep a sharp eye out on the development of this field and how it is shaping our society and interactions with each other.  ...  Artificial intelligence has become the byword for technological progress and is being used in everything from helping us combat the COVID-19 pandemic to nudging our attention in different directions as  ...  From an algorithmic perspective, the authors advocate for the use of a technique called determinantal point process (DPP) that assigns a higher probability score to sets that have higher spreads based  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.14662v1">arXiv:2006.14662v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q76dnqzh4ja5pofurjmpmyeyey">fatcat:q76dnqzh4ja5pofurjmpmyeyey</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201101025243/https://arxiv.org/ftp/arxiv/papers/2006/2006.14662.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ca/96/ca9645dde39fd34bf2057343fefcc99000a2b82e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.14662v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 97 results