Abstract
In Video Question Answering (VideoQA), answering general questions about a video requires its visual information. Yet, video often contains redundant information irrelevant to the VideoQA task. For example, if the task is only to answer questions similar to “Is someone laughing in the video?”, then all other information can be discarded. This paper investigates how many bits are really needed from the video in order to do VideoQA by introducing a novel Few-Bit VideoQA problem, where the goal is to accomplish VideoQA with few bits of video information (e.g., 10 bits). We propose a simple yet effective task-specific feature compression approach to solve this problem. Specifically, we insert a lightweight Feature Compression Module (FeatComp) into a VideoQA model which learns to extract task-specific tiny features as little as 10 bits, which are optimal for answering certain types of questions. We demonstrate more than 100,000-fold storage efficiency over MPEG4-encoded videos and 1,000-fold over regular floating point features, with just 2.0–6.6% absolute loss in accuracy, which is a surprising and novel finding. Finally, we analyze what the learned tiny features capture and demonstrate that they have eliminated most of the non-task-specific information, and introduce a Bit Activation Map to visualize what information is being stored. This decreases the privacy risk of data by providing k-anonymity and robustness to feature-inversion techniques, which can influence the machine learning community, allowing us to store data with privacy guarantees while still performing the task effectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
In the MSRVTT-QA dataset the videos are 630 KB on average, which consists of \(320\times 240\)-resolution videos, 15 s on average.
- 2.
ClipBERT uses 16-bit precision, we use this for calculation.
- 3.
- 4.
numpy.savez_compressed.
- 5.
- 6.
References
Abadi, M., et al.: Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security (2016)
Cambridge, A.L.: The orl database. https://www.cl.cam.ac.uk/research/dtg/ attarchive/facedatabase.html
Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: CVPR (2017)
Chadha, A., Andreopoulos, Y.: Deep perceptual preprocessing for video coding. In: CVPR (2021)
Chen, X., et al.: Microsoft coco captions: data collection and evaluation server. arXiv (2015)
Choi, J., Han, B.: Task-aware quantization network for JPEG image compression. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 309–324. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58565-5_19
Djelouah, A., Campos, J., Schaub-Meyer, S., Schroers, C.: Neural inter-frame compression for video coding. In: ICCV (2019)
Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: ICCV (2019)
Feng, R., Wu, Y., Guo, Z., Zhang, Z., Chen, Z.: Learned video compression with feature-level residuals. In: CVPR Workshops (2020)
Fredrikson, M., Jha, S., Ristenpart, T.: Model inversion attacks that exploit confidence information and basic countermeasures. In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (2015)
Goyal, Y., Khot, T., Summers-Stay, D., Batra, D., Parikh, D.: Making the V in VQA matter: elevating the role of image understanding in visual question answering. In: CVPR, July 2017
He, T., Sun, S., Guo, Z., Chen, Z.: Beyond coding: detection-driven image compression with semantically structured bit-stream. In: PCS (2019)
Hu, Z., Chen, Z., Xu, D., Lu, G., Ouyang, W., Gu, S.: Improving deep video compression by resolution-adaptive flow coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 193–209. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58536-5_12
Hu, Z., Lu, G., Xu, D.: FVC: a new framework towards deep video compression in feature space. In: CVPR (2021)
Huang, D., Chen, P., Zeng, R., Du, Q., Tan, M., Gan, C.: Location-aware graph convolutional networks for video question answering. In: AAAI (2020)
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
Jang, Y., Song, Y., Yu, Y., Kim, Y., Kim, G.: TGIF-QA: toward spatio-temporal reasoning in visual question answering. In: CVPR (2017)
Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV 123, 32–73 (2017)
Le, T.M., Le, V., Venkatesh, S., Tran, T.: Hierarchical conditional relation networks for video question answering. In: CVPR (2020)
Lei, J., et al.: Less is more: ClipBERT for video-and-language learning via sparse sampling. In: CVPR (2021)
Lei, J., Yu, L., Bansal, M., Berg, T.L.: TVQA: localized, compositional video question answering. arXiv preprint arXiv:1809.01696 (2018)
Li, L., Chen, Y.C., Cheng, Y., Gan, Z., Yu, L., Liu, J.: Hero: Hierarchical encoder for video+language omni-representation pre-training. In: EMNLP (2020)
Li, L., Pal, B., Ali, J., Sullivan, N., Chatterjee, R., Ristenpart, T.: Protocols for checking compromised credentials. In: Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (2019)
Lin, J., Liu, D., Li, H., Wu, F.: M-LVC: multiple frames prediction for learned video compression. In: CVPR (2020)
Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: ECCV (2019)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Lu, G., Ouyang, W., Xu, D., Zhang, X., Cai, C., Gao, Z.: DVC: an end-to-end deep video compression framework. In: CVPR (2019)
Mahendran, A., Vedaldi, A.: Understanding deep image representations by inverting them. In: CVPR (2015)
Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: CVPR (2020)
Miech, A., Zhukov, D., Alayrac, J.B., Tapaswi, M., Laptev, I., Sivic, J.: HowTo100M: learning a text-video embedding by watching hundred million narrated video clips. In: ICCV (2019)
Minderer, M., Sun, C., Villegas, R., Cole, F., Murphy, K., Lee, H.: Unsupervised learning of object structure and dynamics from videos. arXiv preprint arXiv:1906.07889 (2019)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV 115(3), 211–252 (2015)
Samarati, P., Sweeney, L.: Protecting privacy when disclosing information: k-anonymity and its enforcement through generalization and suppression (1998)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV (2017)
Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circ. Syst. Video Technol. 22(12), 1649–1668 (2012)
Sun, C., Myers, A., Vondrick, C., Murphy, K., Schmid, C.: VideoBERT: a joint model for video and language representation learning. In: ICCV (2019)
Tapaswi, M., Zhu, Y., Stiefelhagen, R., Torralba, A., Urtasun, R., Fidler, S.: MovieQA: understanding stories in movies through question-answering. In: CVPR (2016)
Toderici, G., et al.: Variable rate image compression with recurrent neural networks. arXiv preprint arXiv:1511.06085 (2015)
Toderici, G., et al.: Full resolution image compression with recurrent neural networks. In: CVPR (2017)
Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: CVPR (2018)
Wallace, G.K.: The JPEG still picture compression standard. IEEE Trans. Consum. Electron. 38, 18–34 (1992)
Wiegand, T., Sullivan, G.J., Bjontegaard, G., Luthra, A.: Overview of the H.264/AVC video coding standard. IEEE Trans. Circ. Syst. Video Technol. 13, 560–576 (2003)
Wu, C.-Y., Singhal, N., Krähenbühl, P.: Video compression through image interpolation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11212, pp. 425–440. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01237-3_26
Xu, D., et al.: Video question answering via gradually refined attention over appearance and motion. In: ACM MM (2017)
Zhu, L., Xu, Z., Yang, Y., Hauptmann, A.: Uncovering the temporal context for video question answering. IJCV 124, 409–421 (2017)
Acknowledgement
We would like to thank Vicente Ordonez for his valuable feedback on the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, S., Piramuthu, R., Chang, SF., Sigurdsson, G.A. (2023). Video in 10 Bits: Few-Bit VideoQA for Efficiency and Privacy. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13805. Springer, Cham. https://doi.org/10.1007/978-3-031-25072-9_49
Download citation
DOI: https://doi.org/10.1007/978-3-031-25072-9_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-25071-2
Online ISBN: 978-3-031-25072-9
eBook Packages: Computer ScienceComputer Science (R0)