Deep Domain Adaptation in Action Space

By Arshad Jamal, Vinay P. Namboodiri, Dipti Deodhare, K. Venkatesh. 2018

92 citations recorded by the source corpus.

Subfields: Reinforcement Learning, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

1. Dima Damen
2. Zsolt Kira
3. Giovanni Maria Farinella
4. Antonino Furnari
5. Jonathan Munro
6. Juan Carlos Niebles

In Representation & Self-Supervised Learning

1. Dima Damen
2. Jonathan Munro
3. Giovanni Maria Farinella
4. Antonino Furnari
5. Barbara Caputo
6. Emanuele Alberti
7. Chiara Plizzari
8. Mirco Planamente

Citations in the corpus

• Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, background): “A-C [88] 280157 N/A 12 3 1 N/A 2017 Real/Syn DomainNet [89] 363534 37706 345 6 1 N/A 2019 Real/Syn Source Target Target Test Video UCF$HMDB (small) [95] 482 350 150 5 2 1 4:72:5 2018 Real UCF$Olympic [90] 601 250 54 6 2 1 6:64:5 2018 Real UCF$HMDB (full) [91] 1438 840 360 12 2 1 4:05:8 2019 Real IEM”
• Adversarial Cross-Domain Action Recognition with Co-Attention (2019, methodology): “Previous cross-domain action recognition meth-ods directly match segment feature distributions (Jamal et al. 2018) or with weights based on an attention mechanism (Chen et al. 2019).”
• Cross-Domain First Person Audio-Visual Action Recognition through Relative Norm Alignment (2021, background): “Only few works analyzed UDA for video understanding [10, 41, 11, 25].”
• Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (2019, methodology): “When evaluating on UCF-HMDBsmall, AMLS [17] finetunes their networks using UCF and HMDB, respectively, before applying their DA approach.”
• Multi-Modal Domain Adaptation for Fine-Grained Action Recognition (2020, methodology): “However, very few works have attempted deep UDA for video data [7, 19].”
• Multi-Modal Domain Adaptation for Fine-Grained Action Recognition (2019, methodology): “However, very few works have attempted deep UDA for video data [7, 19].”