Pith. sign in

Paper Citation Record · LEDGER

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing

As of 13 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2411.10198.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2411.10198 v1

Coverage vector

measured 59 of 59 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:55:10.160611Z

measured 59 of 59 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-13T06:32:02.005865+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

59 of 59 outbound references displayed

  • verified exact1
  • verified fuzzy37
  • unresolved21
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation e5777d03-5ff1-443a-a5f0-87f279d05695 · outbound

This paper cites Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Driving

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.879994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.879994Z digest=sha256:0f665c23ec2d7c034ebbf3b8fff0573bd6035adf63b6566060869464d7de01b1

Observation 6d2589de-e0d0-4049-8370-2db9103bb5fd · outbound

This paper cites Efficient prediction of human motion for real-time robotics applica- tions with physics-inspired neural networks.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Efficient prediction of human motion for real-time robotics applica- tions with physics-inspired neural networks

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.753108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.884272Z digest=sha256:dc09c606a898ed26aa2e7bf22e578acbd0bd3bb44948e0f3e78a9cb60c5e2ba5

Observation a9e73dc2-6be2-4a4f-9ea8-ffcd7077f554 · outbound

This paper cites Anticipating many futures: Online human motion predic- tion and generation for human-robot interaction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Anticipating many futures: Online human motion predic- tion and generation for human-robot interaction

Reference 3

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.743772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.887668Z digest=sha256:3374c70568fc59bea112e75a4f4fdf64c434ae9aad6b2fc03b30c8e6a05763d7

Observation 50b3ed71-f205-4890-a6be-16949e6fdad2 · outbound

This paper cites Mau: A motion- aware unit for video prediction and beyond.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Mau: A motion- aware unit for video prediction and beyond

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.890962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.890962Z digest=sha256:595153649ebff8adb837f2afc8ed6f171a8db16e8f243bb7b0f8e3860345d1b7

Observation d99d91fc-8f5d-4584-8408-deaf31cd9514 · outbound

This paper cites CycleMLP: A MLP-like Architecture for Dense Prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing CycleMLP: A MLP-like Architecture for Dense Prediction

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.893992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.893992Z digest=sha256:f3ff27cf3063988f707fcca771c7573fa078fd72e37c48d668907a582d2e4132

Observation 23d454bc-d45f-49c8-9d13-9f9ab43a7c5b · outbound

This paper cites Spatio-temporal image representation and deep- learning-based decision framework for automated vehicles.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Spatio-temporal image representation and deep- learning-based decision framework for automated vehicles

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.730314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.897395Z digest=sha256:f7371301e4af24831c7925d15eb1edfe30d1a93976aa6a840e2bd33e1e5b3816

Observation d42c47b9-64e7-465a-b7b0-5944ff774ba5 · outbound

This paper cites Inductive Bias of Deep Convolutional Networks through Pooling Geometry.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Inductive Bias of Deep Convolutional Networks through Pooling Geometry

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.900519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.900519Z digest=sha256:9a1a1f0b0d7a0e997811fe142287f173d6f739b54df6894d2f479a073a9e91ff

Observation 69732bd6-a4a7-4ced-8c8a-5cc0d968d063 · outbound

This paper cites Pedestrian detection: A benchmark.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Pedestrian detection: A benchmark

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.720989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.904012Z digest=sha256:fdd4ffc077cdec101249aeec4421fdaceab4f496045fb863843e2432b64ba069

Observation c20f7826-48b0-4f95-b329-b770ced21ef2 · outbound

This paper cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.906615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.906615Z digest=sha256:ba526b2b259897dfb4df52dbf92a639446320569baaf19fa500de830fd972373

Observation 50377bd2-a4fa-4edd-b446-b22de1ed79cf · outbound

This paper cites an unresolved cited work.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Unresolved cited work

Reference 10

Resolution
unresolved
raw_fallback, observed 2026-08-12T19:55:10.711945Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.909309Z digest=sha256:895516bb632c9b98e14ddb2d69e3dbef63cd04c7510cda68130e170c37b95c41

Observation f6fda495-c83d-49ca-94ce-ccf1f0aea0b5 · outbound

This paper cites Simvp: Simpler yet better video prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Simvp: Simpler yet better video prediction

Reference 11

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.703097Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.912191Z digest=sha256:307d8586d04a13a3ad1e7aabea69f4484de1cc5abba2dd56f6df4aeb7e97e272

Observation 2764772a-c992-46ca-9dfc-d2ebfce0fc52 · outbound

This paper cites Are we ready for autonomous driving? the kitti vision benchmark suite.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Are we ready for autonomous driving? the kitti vision benchmark suite

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.914851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.914851Z digest=sha256:74112a9bef0a4c111c9d0ff6655947cc0d9f40d846c26e4bd93773b175ba6141

Observation 08ae71b8-c179-4fe4-9096-e7b4cd49916a · outbound

This paper cites Deep Learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Deep Learning

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.917418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.917418Z digest=sha256:43003a42402a17aabb53233800461bd19a57d4ca31254e384abb6abff71adff6

Observation 0772fabc-2202-4f45-8b9c-1e603b1beca5 · outbound

This paper cites Disentangling physi- cal dynamics from unknown factors for unsupervised video prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Disentangling physi- cal dynamics from unknown factors for unsupervised video prediction

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.683923Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.919685Z digest=sha256:8e0374d1ff0ecc2e71e274a678da0503a2fd60999f35416cc5edd70d2d604bc0

Observation 04553204-7548-41cf-96a0-51125296c589 · outbound

This paper cites Classifying pedestrian actions in advance using predicted video of urban driving scenes.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Classifying pedestrian actions in advance using predicted video of urban driving scenes

Reference 15

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.674301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.922219Z digest=sha256:db0c61b1bfe3933a41878932bfe75f071b5126dc0db7423d80ab8cab097f12db

Observation 16f630af-a0a6-4fd9-af4b-fbee7a8eb2b6 · outbound

This paper cites Delving deep into rectifiers: Surpassing human-level perfor- mance on imagenet classification.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Delving deep into rectifiers: Surpassing human-level perfor- mance on imagenet classification

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.665418Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.924785Z digest=sha256:d15dda04f9fd38c5a61fe1c2d0d2bf69abd510ee881fc136d8a370f6b3d1f2be

Observation 1565775c-f41a-46b4-bdca-f85958e0698c · outbound

This paper cites A dynamic multi-scale voxel flow network for video prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing A dynamic multi-scale voxel flow network for video prediction

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.656790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.927386Z digest=sha256:17d416fb5f24f52129f86a364c8defbdc7816fa16d068cccb0f4d81f03798b4a

Observation 0ad150f8-76c1-4256-bf94-cb6003ea3c92 · outbound

This paper cites Learning robot activities from first-person human videos using convolutional future regression.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Learning robot activities from first-person human videos using convolutional future regression

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.648105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.930174Z digest=sha256:defb6a0987952da094ff51fdbb93dfef73bc5bb4fab1d3d6137e0f8f7f9aaf8a

Observation 647fdc14-3417-45e3-be95-06c96b132448 · outbound

This paper cites More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.933222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.933222Z digest=sha256:09a99ac614967f436a5e1bee3a5e63a68bbb4a5ffdd7698e63420a6d39a2f2c6

Observation 657789a7-b35b-41ab-9cff-41f0d1a98c1b · outbound

This paper cites A convnet for the 2020s.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing A convnet for the 2020s

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.936500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.936500Z digest=sha256:e63a80fbd641b62719448fb577f7a53a864f4fc671aedb3aa47ee36ba3b7b1c6

Observation 55447e5a-e6ad-4df6-8927-c961ec82c19e · outbound

This paper cites Video frame synthesis using deep voxel flow.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Video frame synthesis using deep voxel flow

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.634447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.939601Z digest=sha256:cbc76b24ff63e2931fb0c31970e948f5db2d2a98c32960fc6ab152f9246d256f

Observation 82649d70-2b67-47e1-a124-48a8d8811d83 · outbound

This paper cites Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.942565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.942565Z digest=sha256:69ab8b1102e4b26228a8903ee8b98da69bb7413db7f9ab154d2f5b92d947868b

Observation 04284588-8a6b-442d-83bd-d63389370dab · outbound

This paper cites Predicting fu- ture occupancy grids in dynamic environment with spatio- temporal learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predicting fu- ture occupancy grids in dynamic environment with spatio- temporal learning

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.625763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.946392Z digest=sha256:9deb6e490934717a986393c4aa757e80efd38df812281b8df4e6ae90225a2d9b

Observation e396159f-c377-4e1f-9ab0-560ce6ea3955 · outbound

This paper cites U- net: Convolutional networks for biomedical image segmen- tation.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing U- net: Convolutional networks for biomedical image segmen- tation

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.949652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.949652Z digest=sha256:4d0fdf0aa52fe1670ae7220424b7ac27b6c89f19cb13170c30b411b5bda3d53f

Observation 6c2a9ddc-30cd-4de6-9347-71bf1da99e77 · outbound

This paper cites Rousseeuw.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Rousseeuw

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.612231Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.952947Z digest=sha256:0bd63454f025bce728f9f692b375af5d9b535408b6cb764af27dbb12673092fb

Observation dcd96fd4-bcef-4f77-9aa3-4cfb7e5d9f07 · outbound

This paper cites Recog- nizing human actions: a local svm approach.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Recog- nizing human actions: a local svm approach

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.956213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.956213Z digest=sha256:4fa5390c7364167c3e77d6c402baf7ef0dfe0505c744c432e9ae2295195aff6c

Observation f4b0a008-30d1-4184-9d92-a3ae74ed0269 · outbound

This paper cites Implicit Stacked Autoregressive Model for Video Prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Implicit Stacked Autoregressive Model for Video Prediction

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.963407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.963407Z digest=sha256:6b0da45d22afc5ef452b55147ec902cbebdf3db3e832e4849df322b28b6cc15c

Observation 431d08fa-3fe7-45a2-b78a-abad8853365d · outbound

This paper cites Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.966909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.966909Z digest=sha256:179a3a8767b64fbdb52e73f0c1a7bf4a4ce85307ff52401f89d134dccf130db3

Observation 150d773e-feac-4f95-8f08-c66ffe134647 · outbound

This paper cites Convolutional lstm network: A machine learning approach for precipitation nowcasting.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Convolutional lstm network: A machine learning approach for precipitation nowcasting

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.581979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.970228Z digest=sha256:ae17e8d091f7aebe96f722806fd5cd8f8807397ff3c62490f0133f1c299e8ab7

Observation c288bac3-bbc1-486d-a469-777707d57e36 · outbound

This paper cites Unsupervised learning of video representations using lstms.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Unsupervised learning of video representations using lstms

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.571141Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.973450Z digest=sha256:8bc04c4f1739fbc09a7407110acc1fbff27f00155cc3eaa9b7ab3d41c7917f6c

Observation 0056a8f2-5450-4995-aea4-a61471281ed8 · outbound

This paper cites Sequence to sequence learning with neural networks.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Sequence to sequence learning with neural networks

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.559718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.976605Z digest=sha256:190eb16b6d64e48466561d245cbfab5f4a684c82c6455cd446e0187ee65e578a

Observation 2ae2aa7b-7ecd-4db6-99d4-58a4101bb3b4 · outbound

This paper cites Going deeper with convolutions.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Going deeper with convolutions

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.548620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.979780Z digest=sha256:0546b1e2d8ce55d9750caf08f04619e4bac050e5ab3316fecad7f0309cd9a478

Observation 2c6c98ad-0ee5-47bb-a47f-7c89c21adc55 · outbound

This paper cites Temporal attention unit: To- wards efficient spatiotemporal predictive learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Temporal attention unit: To- wards efficient spatiotemporal predictive learning

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.536983Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.982775Z digest=sha256:adde1ce3ebd9bc8649a6137ff4d999bb1eb186c79095c34a31404d2674af6466

Observation 520de40a-a81d-411d-a512-4db84a6e8289 · outbound

This paper cites OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:09.985653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:09.985653Z digest=sha256:c0ddaee0f3f0f3b0fa112006721e0776b393d50d705516fec350e81f63a772b9

Observation b2667f17-4a86-43e3-aa63-902f4198f3c2 · outbound

This paper cites Mlp-mixer: An all-mlp architecture for vision.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Mlp-mixer: An all-mlp architecture for vision

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:10.089112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:10.089112Z digest=sha256:98390876743248447c95c73620312cf3cd299a9ad7e104fa504f4062f7ecd345

Observation ddb5b90f-1da9-4f36-a3f8-d5ffe95827c3 · outbound

This paper cites Resmlp: Feedforward networks for image classification with data-efficient training.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Resmlp: Feedforward networks for image classification with data-efficient training

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.518467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.092669Z digest=sha256:a5d51315f4a4b65c4ea077b04ea87dfbd5a764466f1a47305b015ebf1ba09cf0

Observation 545d3cc4-fb19-4c6e-b179-508df48ec8f2 · outbound

This paper cites Patches Are All You Need?.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Patches Are All You Need?

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:10.095375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:10.095375Z digest=sha256:d4c11876d98929a2cd33a6a8dabc4ddb25ae042e9131b29f3a71385f96273fb0

Observation d2166c17-3fca-43b6-b003-0ed4251648db · outbound

This paper cites Attention is all you need.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Attention is all you need

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:10.098176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:10.098176Z digest=sha256:780464320170c2301f955ff5e3435369ed8bc70ca5a88f77be6f466f7f80f5a5

Observation 0e04bd53-2c22-4280-9d10-91247394ed15 · outbound

This paper cites Decomposing Motion and Content for Natural Video Sequence Prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Decomposing Motion and Content for Natural Video Sequence Prediction

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:10.100677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:10.100677Z digest=sha256:98f346dda0f3a36c90451df54dd016aa41a531eede938cd6780c4fb4c33b3d8d

Observation 0f8393fe-66e5-44b4-829c-4266eaceb0a1 · outbound

This paper cites Mcvd-masked conditional video diffusion for prediction, generation, and interpolation.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Mcvd-masked conditional video diffusion for prediction, generation, and interpolation

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.501337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.103450Z digest=sha256:d6eabf4e4dbc5078e690f56c05cddae54caa2bae35536d33a507e36334b80146

Observation c8835ff8-8246-4f36-8664-f65e3fb46588 · outbound

This paper cites Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predrnn++: Towards a resolution of the deep-in-time dilemma in spatiotemporal predictive learning

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.491059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.105988Z digest=sha256:115821d643bdb4b534b434b7abd35a2601954dd07eeb50061e4ac13824cbafa3

Observation ec406a26-d675-4a55-a465-2e6b5ff2c5fe · outbound

This paper cites Eidetic 3d lstm: A model for video prediction and beyond.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Eidetic 3d lstm: A model for video prediction and beyond

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.480599Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.108647Z digest=sha256:24cc6d18c997ca3df04579006dbd67e184bb6433838ec1bd36ea37502a452d45

Observation 1f622742-611c-4b66-9fe0-17ed6ce478b8 · outbound

This paper cites Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.469997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.111410Z digest=sha256:702a8de06a30dd0f01dd0e9bb3b545ea0ddb9d235403f8a3f574d2263cabda30

Observation 435b323a-4813-4668-a466-8e42d1ddde0b · outbound

This paper cites Predrnn: A recurrent neural network for spatiotemporal predictive learn- ing.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predrnn: A recurrent neural network for spatiotemporal predictive learn- ing

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.458770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.114041Z digest=sha256:6ac8b74e1ba7ee9797ec099932bf277551fb27a37e3b75e7668e7315080b8f4f

Observation 8bc093b9-fee4-4230-9f56-33da4aa15339 · outbound

This paper cites Memory in memory: A predictive neural network for learning higher-order non- stationarity from spatiotemporal dynamics.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Memory in memory: A predictive neural network for learning higher-order non- stationarity from spatiotemporal dynamics

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.446446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.116823Z digest=sha256:f1fbe8e11548e721813280456065894d9545ce9a1608e73de56a54e5d58ca259

Observation dedf46c7-7b0d-4fa4-8d39-9f790af1bd2b · outbound

This paper cites Sample-efficient reinforcement learning via conservative model-based actor-critic.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Sample-efficient reinforcement learning via conservative model-based actor-critic

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.435383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.119511Z digest=sha256:df81370cb2b677ef4a5d8e6184202159078098ac81485ab202a2e07ba6cf27e1

Observation c4d95904-2d0a-4fe7-baf2-deb7c58ba17f · outbound

This paper cites Theoretical analysis of the induc- tive biases in deep convolutional networks.Advances in Neu- ral Information Processing Systems, 36, 2024.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Theoretical analysis of the induc- tive biases in deep convolutional networks.Advances in Neu- ral Information Processing Systems, 36, 2024

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.424405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.122114Z digest=sha256:e57b6fc50f325cfbd1ffe74a1fd39c1cd80596cd24e5e71461e3016797b1f127

Observation 873ac086-634e-4bf4-9d1b-d951b401824d · outbound

This paper cites Sample efficient deep reinforcement learning for dialogue systems with large action spaces.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Sample efficient deep reinforcement learning for dialogue systems with large action spaces

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.413269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.125281Z digest=sha256:bdd4788842435b684a1afd655bca315d61aff94e32c13d6017b41c486c4cbef1

Observation 812dfe92-d89b-4203-834f-2ab7a377edfd · outbound

This paper cites PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction

Reference 49

Resolution
verified exact
local_arxiv, observed 2026-08-12T19:55:10.198506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.128731Z digest=sha256:8dbc2843fae16f5ec2d5c198f39cc24e19eacc93b136dd639ed728acea2e18da

Observation 3e1e0875-42d6-4c05-9cdd-57a28977a129 · outbound

This paper cites Predcnn: Predictive learning with cascade convo- lutions.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predcnn: Predictive learning with cascade convo- lutions

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.402625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.132269Z digest=sha256:03a83d59f76217c09162a05993a45a2d71189058c71bb86389168a7f3f3c1139

Observation b57a6bbb-7f66-410a-adea-5d321787510e · outbound

This paper cites Vptr: Efficient transformers for video prediction.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Vptr: Efficient transformers for video prediction

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-12T19:55:10.135815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T19:55:10.135815Z digest=sha256:ea47da7b64224119077b67b8ac75fc479f5b174a4814276d805494ae5c70ec97

Observation fcada6cc-c360-4ba9-b884-e11d7d8f2726 · outbound

This paper cites Crevnet: Conditionally reversible video prediction, 2019.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Crevnet: Conditionally reversible video prediction, 2019

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.385153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.139511Z digest=sha256:af7c73f5fef8998a7614f8cc7e662cf1d89896feb87f3e1165d71f13fc947b4c

Observation fc2a83ea-2d41-4fbd-afdf-da3979ab0e83 · outbound

This paper cites Efficient and information-preserving future frame prediction and beyond.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Efficient and information-preserving future frame prediction and beyond

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.374895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.142982Z digest=sha256:f79e6ca239c08084184acb18ca70ee70eea44635d5daf20e11502d33cbc453d1

Observation fee79c12-bdc3-4ee3-a631-a6f8027b93ab · outbound

This paper cites Predicting citywide crowd flows using deep spatio-temporal residual networks.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Predicting citywide crowd flows using deep spatio-temporal residual networks

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.363158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.146576Z digest=sha256:08572cc5555a329f9b3c46bcdf37de2550f9fc31a1bcbd9b9ff0a8a0d74b0120

Observation eea4b4fd-078d-434c-a64e-02952c8556b0 · outbound

This paper cites Pose-forecasting aided human video prediction with graph convolutional networks.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Pose-forecasting aided human video prediction with graph convolutional networks

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.352472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.150030Z digest=sha256:936d2afd0b9f770e3b30589631d36405d7d9a6e53fd9873f59714bca1357ef40

Observation 509ec157-59dc-44d0-86f7-d84a13688fe3 · outbound

This paper cites • Repeated STLMixer The parameter count from our proposed STLMixer architecture is O de · (d2 + d · k2 T1 + d · k2 T2 ).

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing • Repeated STLMixer The parameter count from our proposed STLMixer architecture is O de · (d2 + d · k2 T1 + d · k2 T2 )

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.341162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.153668Z digest=sha256:cd6073531ff32407651679976593824370be851fc401302198dcba1785430202

Observation 54079ed0-07ea-4e2a-809c-6eaaa7ecc0fe · outbound

This paper cites Similarly k2 T1 ≪ d and k2 T2 ≪ d.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing Similarly k2 T1 ≪ d and k2 T2 ≪ d

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.330379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.157250Z digest=sha256:16022fca87ba516bbae0aecdcbf958635521ffeff42962d422172a97e37e1460

Observation b428b63e-bcd1-4d3d-9ca7-bc7a65cd4388 · outbound

This paper cites dis- persion.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing dis- persion

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.319729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:10.160611Z digest=sha256:908c380ab53b59e20dfd02bacba43432452e4c6b3d99e8155651a0f3f0aec75e

Observation 1a87e3e7-f773-49bf-8522-5f2e505db882 · outbound

This paper cites IEEE, 2004.

STLight: a Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal joint Processing IEEE, 2004

Reference 2004

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T19:55:10.597816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.

source=pdf_text observed=2026-08-12T19:55:09.959596Z digest=sha256:30c55cec64ae3a51d59c104db238822d413b0efd40166b6c9df4ed59b5faf808

Pith citing papers

No inbound Pith citation observations are available.