Bibliography:

1. ​ ‘AI video’ tag

2. ​ ‘CLIP’ tag

3. ​ ‘masked autoencoder’ tag

4. ​ CT Foundation: Taking medical imaging embeddings 3D

5. ​ Long-Term Tracking of Social Structure in Groups of Rats

6. ​ Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

7. ​ InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

8. ​ Test-Time Training on Video Streams

9. ​ Magenta Green Screen: Spectrally Multiplexed Alpha Matting with Deep Colorization

10. ​ PaLI-X: On Scaling up a Multilingual Vision and Language Model

11. ​ ImageBind: One Embedding Space To Bind Them All

12. ​ Scaling Vision Transformers to 22 Billion Parameters

13. ​ VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners

14. ​ VindLU: A Recipe for Effective Video-and-Language Pretraining

15. ​ Videogenic: Video Highlights via Photogenic Moments

16. ​ AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies

17. ​ Vision-Language Pre-training: Basics, Recent Advances, and Future Trends

18. ​ TVLT: Textless Vision-Language Transformer

19. ​ EVL: Frozen CLIP Models are Efficient Video Learners

20. ​ X-CLIP: Expanding Language-Image Pretrained Models for General Video Recognition

21. ​ X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

22. ​ Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

23. ​ OmniMAE: Single Model Masked Pretraining on Images and Videos

24. ​ LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

25. ​ MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing

26. ​ Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs

27. ​ Revisiting the "Video" in Video-Language Understanding

28. ​ VidIL: Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

29. ​ Masked Autoencoders As Spatiotemporal Learners

30. ​ Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning

31. ​ ViS4mer: Long Movie Clip Classification with State-Space Video Models

32. ​ Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

33. ​ Reinforcement Learning with Action-Free Pre-Training from Videos

34. ​ CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning

35. ​ Robot peels banana with goal-conditioned dual-action deep imitation learning

36. ​ Hierarchical Perceiver

37. ​ MuZero with Self-competition for Rate Control in VP9 Video Compression

38. ​ BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

39. ​ MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition

40. ​ CAST: Character labeling in Animation using Self-supervision by Tracking

41. ​ AV-HuBERT: Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction

42. ​ Noether Networks: Meta-Learning Useful Conserved Quantities

43. ​ MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions

44. ​ MorphMLP: A Self-Attention Free, MLP-Like Backbone for Image and Video

45. ​ Florence: A New Foundation Model for Computer Vision

46. ​ Scaling ASR Improves Zero and Few Shot Learning

47. ​ ADOP: Approximate Differentiable One-Pixel Point Rendering

48. ​ VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

49. ​ Perceiver IO: A General Architecture for Structured Inputs & Outputs

50. ​ CLIP-It! Language-Guided Video Summarization

51. ​ CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

52. ​ Revisiting ResNets: Improved Training and Scaling Strategies

53. ​ Learning from videos to understand the world

54. ​ Perceiver: General Perception with Iterative Attention

55. ​ Video Transformer Network

56. ​ Automatic Curation of Large-Scale Datasets for Audio-Visual Representation Learning

57. ​ MSR-VTT: A Large Video Description Dataset for Bridging Video and Language

58. ​ CLIP: Learning Transferable Visual Models From Natural Language Supervision

59. ​ Transformers in Vision: A Survey

60. ​ Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures

61. ​ Accuracy and Performance Comparison of Video Action Recognition Approaches

62. ​ Self-supervised learning through the eyes of a child

63. ​ Gesticulator: A framework for semantically-aware speech-driven gesture generation

64. ​ SAYCam: A large, longitudinal audiovisual dataset recorded from the infant’s perspective

65. ​ Axial Attention in Multidimensional Transformers

66. ​ CATER: A diagnostic dataset for Compositional Actions and TEmporal Reasoning

67. ​ CLEVRER: CoLlision Events for Video REpresentation and Reasoning

68. ​ Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos

69. ​ A Short Note on the Kinetics-700 Human Action Dataset

70. ​ Billion-scale semi-supervised learning for image classification

71. ​ VideoBERT: A Joint Model for Video and Language Representation Learning

72. ​ Real-time Continuous Transcription with Live Transcribe

73. ​ CCNet: Criss-Cross Attention for Semantic Segmentation

74. ​ Evolving Space-Time Neural Architectures for Videos

75. ​ Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow

76. ​ A Short Note about Kinetics-600

77. ​ Large-Scale Visual Speech Recognition

78. ​ Playing hard exploration games by watching YouTube

79. ​ BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning

80. ​ The Sound of Pixels

81. ​ One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

82. ​ Learning Compact Recurrent Neural Networks with Block-Term Tensor Decomposition

83. ​ Reinforced Video Captioning with Entailment Rewards

84. ​ Tracking as Online Decision-Making: Learning a Policy from Streaming Videos with Reinforcement Learning

85. ​ Learning to Learn from Noisy Web Videos

86. ​ Quo Vadis, Action Recognition? A New Model I3D and the Kinetics Dataset

87. ​ The Kinetics Human Action Video Dataset

88. ​ Dense-Captioning Events in Videos

89. ​ Time-Contrastive Networks: Self-Supervised Learning from Video

90. ​ LipNet: End-to-End Sentence-level Lipreading

91. ​ Deep Visual Foresight for Planning Robot Motion

92. ​ Temporal Convolutional Networks: A Unified Approach to Action Segmentation

93. ​ Clockwork Convnets for Video Semantic Segmentation

94. ​ Artistic style transfer for videos

95. ​ YFCC100M: The New Data in Multimedia Research

96. ​ UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild

97. ​ design#future-tag-features

    [Transclude the forward-link's context]

98. ​ 2022-baker-figure8-vptsuccessratescalingofmakingitemsbydatasetsizescaling.png

99. ​ 2021-lee-figure4-datascaling.png

100. ​ https://ai.meta.com/blog/v-jepa-yann-lecun-ai-model-video-joint-embedding-predictive-architecture/

101. ​ 759e50847f76f686f333cf2d92d46f60f3539f48.html

102. ​ https://github.com/facebookresearch/jepa

103. ​ ad8c5fa97c6ea2c2011978d7fd9a6e215d7aef57.html

104. ​ https://openai.com/research/vpt

105. ​ https://rmozone.com/snapshots/2021/11/gentle-history/

106. ​ https://simonwillison.net/2024/Feb/21/gemini-pro-video

107. ​ 1cee0912bf1331b2bc9b97f4bebb4933d571ddc0.html

108. ​ https://www.csm.ai/commonsim-1-generating-3d-worlds

109. ​ https://www.nature.com/articles/s42003-023-05098-1

110. ​ CT Foundation: Taking medical imaging embeddings 3D

111. ​ https%253A%252F%252Fresearch.google%252Fblog%252Ftaking-medical-imaging-embeddings-3d%252F.html

112. ​ Test-Time Training on Video Streams

113. ​ Yu Sun

114. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2307.05014.html

115. ​ ImageBind: One Embedding Space To Bind Them All

116. ​ Zhuang Liu’s Homepage

117. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2305.05665%2523facebook.html

118. ​ Scaling Vision Transformers to 22 Billion Parameters

119. ​ Robert Geirhos

120. ​ Lucas Beyer

121. ​ Yi Tay

122. ​ Neil Houlsby

123. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2302.05442%2523google.html

124. ​ VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners

125. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2212.04979%2523google.html

126. ​ VindLU: A Recipe for Effective Video-and-Language Pretraining

127. ​ Mohit Bansal

128. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2212.05051.html

129. ​ TVLT: Textless Vision-Language Transformer

130. ​ Mohit Bansal

131. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2209.14156.html

132. ​ EVL: Frozen CLIP Models are Efficient Video Learners

133. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2208.03550.html

134. ​ X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval

135. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2207.07285%2523alibaba.html

136. ​ Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

137. ​ Jeff Clune—Professor—Computer Science—University of British Columbia

138. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2206.11795%2523openai.html

139. ​ OmniMAE: Single Model Masked Pretraining on Images and Videos

140. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2206.08356%2523facebook.html

141. ​ LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling

142. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2206.07160%2523microsoft.html

143. ​ VidIL: Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners

144. ​ Mohit Bansal

145. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2205.10747.html

146. ​ Masked Autoencoders As Spatiotemporal Learners

147. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2205.09113%2523facebook.html

148. ​ Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

149. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2204.00598%2523google.html

150. ​ CLIP meets GamePhysics: Towards bug identification in gameplay videos using zero-shot transfer learning

151. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2203.11096.html

152. ​ BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

153. ​ Caiming Xiong—Home Page

154. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2201.12086%2523salesforce.html

155. ​ Florence: A New Foundation Model for Computer Vision

156. ​ Jianfeng Gao at Microsoft Research

157. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2111.11432%2523microsoft.html

158. ​ Perceiver IO: A General Architecture for Structured Inputs & Outputs

159. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2107.14795%2523deepmind.html

160. ​ CLIP-It! Language-Guided Video Summarization

161. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2107.00650.html

162. ​ CLIP2Video: Mastering Video-Text Retrieval via Image CLIP

163. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2106.11097.html

164. ​ Revisiting ResNets: Improved Training and Scaling Strategies

165. ​ Aravind Srinivas

166. ​ Barret Zoph

167. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2103.07579%2523google.html

168. ​ Learning from videos to understand the world

169. ​ Polina Kuznetsova

170. ​ https%253A%252F%252Fai.facebook.com%252Fblog%252Flearning-from-videos-to-understand-the-world%252F.html

171. ​ Perceiver: General Perception with Iterative Attention

172. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2103.03206%2523deepmind.html

173. ​ CLIP: Learning Transferable Visual Models From Natural Language Supervision

174. ​ Alec Radford

175. ​ Jong Wook Kim

176. ​ Aditya A. Ramesh

177. ​ Sandhini Agarwal

178. ​ About Me

179. ​ https://jack-clark.net/about/

180. ​ Gretchen Krueger

181. ​ https%253A%252F%252Fcdn.openai.com%252Fpapers%252FLearning_Transferable_Visual_Models_From_Natural_Language_Supervision.pdf.html

182. ​ Object-based attention for spatio-temporal reasoning: Outperforming neuro-symbolic models with flexible distributed architectures

183. ​ Language Understanding Grounded in Perception and Action

184. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2012.08508%2523deepmind.html

185. ​ Accuracy and Performance Comparison of Video Action Recognition Approaches

186. ​ https%253A%252F%252Farxiv.org%252Fabs%252F2008.09037.html

187. ​ Billion-scale semi-supervised learning for image classification

188. ​ https%253A%252F%252Farxiv.org%252Fabs%252F1905.00546%2523facebook.html

189. ​ CCNet: Criss-Cross Attention for Semantic Segmentation

190. ​ https%253A%252F%252Farxiv.org%252Fabs%252F1811.11721.html

191. ​ A Short Note about Kinetics-600

192. ​ https%253A%252F%252Farxiv.org%252Fabs%252F1808.01340%2523deepmind.html

193. ​ Quo Vadis, Action Recognition? A New Model I3D and the Kinetics Dataset

194. ​ https%253A%252F%252Farxiv.org%252Fabs%252F1705.07750%2523deepmind.html

195. ​ Clockwork Convnets for Video Semantic Segmentation

196. ​ https%253A%252F%252Farxiv.org%252Fabs%252F1608.03609.html

197. Wikipedia Bibliography:

     1. ​ Alexei A. Efros

     2. ​ Xiao Wang

     3. ​ Tao Zhu

     4. ​ Yuan Cao

     5. ​ Mi Zhang

     6. ​ Soham Ghosh

     7. ​ Ming Yan

     8. ​ Jie Tang

     9. ​ Kevin Lin

     10. ​ Zicheng Liu

     11. ​ Shih-Fu Chang

     12. ​ Heng Ji

     13. ​ Kaiming He

     14. ​ Xuedong Huang

     15. ​ Yu Shi

     16. ​ David Ding

     17. ​ Andrew Brock

     18. ​ Andrew Zisserman

     19. ​ Oriol Vinyals

     20. ​ Trevor Darrell

     21. ​ Ilya Sutskever

     22. ​ Matthew Hutchinson

     23. ​ Andrew Prout

     24. ​ Thomas S. Huang

     25. ​ Judy Hoffman