The DOI matches its Crossref record; 36 of the 37 references it cites were found in a registry or an index.
Direct face detection and video reconstruction from event cameras
Abstract
Event cameras are emerging as a new class of cameras, to potentially rival conventional CMOS cameras, because of their high speed operation and low power consumption. Pixels in an event camera operate in parallel and fire asynchronous spikes when individual pixels encounter a change in intensity that is greater than a pre-determined threshold. Such event-based cameras have an immense potential in battery-operated or always-on application scenarios, owing to their low power consumption. These event-based cameras can be used for direct detection from event streams, and we demonstrate this potential using face detection as an example application. We first propose and develop a patch-based model for the event streams acquired from such cameras. We demonstrate the utility and robustness of the patch-based model for event-based video reconstruction and event-based direct face detection. We are able to reconstruct images and videos at over 2,000 fps from the acquired event streams. In addition, we demonstrate the first direct face detection from event streams, highlighting the potential of these event-based cameras for power-efficient vision applications.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Recently, deep neural network-based event-to-image conversion models [8]-[11] have demonstrated impressive abilities in recovering gray-scale images from event streams, posing a potential risk to the privacy aspect of event-based vision applications.”
From Event Anonymization: Privacy-Preserving Person Re-Identification and Pose Estimation in Event-Based Vision (2024) · cites this paper as [36]
Citations
Cites
Histograms of Oriented Gradients for Human Detection
Dalal, N., & Triggs, B. (2005) · 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) · doi:10.1109/cvpr.2005.177 · Cited by 33,584
Rapid object detection using a boosted cascade of simple features
Viola, P., & Jones, M. (2005) · Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001 · doi:10.1109/cvpr.2001.990517 · Cited by 18,300
Robust Real-Time Face Detection
Viola, P., & Jones, M. J. (2004) · International Journal of Computer Vision · doi:10.1023/b:visi.0000013087.49260.fb · Cited by 14,097
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. M. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,464
Martin, D., Fowlkes, C., Tal, D., & Malik, J. (2002) · Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 · doi:10.1109/iccv.2001.937655 · Cited by 8,216
Image Denoising Via Sparse and Redundant Representations Over Learned Dictionaries
Elad, M., & Aharon, M. (2006) · IEEE Transactions on Image Processing · doi:10.1109/tip.2006.881969 · Cited by 5,321
Image Super-Resolution Via Sparse Representation
Yang, J., Wright, J. N., Huang, T. S., & Ma, Y. (2010) · IEEE Transactions on Image Processing · doi:10.1109/tip.2010.2050625 · Cited by 5,241
Pati, Y., Rezaiifar, R., & Krishnaprasad, P. (1993) · Proceedings of 27th Asilomar Conference on Signals, Systems and Computers · doi:10.1109/acssc.1993.342465 · Cited by 4,928
A 128$\times$128 120 dB 15 $\mu$s Latency Asynchronous Temporal Contrast Vision Sensor
Lichtsteiner, P., Posch, C., & Delbruck, T. (2008) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2007.914337 · Cited by 2,485 · cited 13×
“Data Finally, we conduct face detection experiments using real event streams from the DVS128.”
BackgroundMethodInfluentialFace detection, pose estimation, and landmark localization in the wild
Zhu, X., & Ramanan, D. (2012) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2012.6248014 · Cited by 2,171
Flagged first, then by citations
1 of the 37 references couldn’t be matched to a known paper.
Research works printed but not linked: 3
- Grasshopper3 4.1 mp mono usb3 vision (cmosis cmv40003e5)
- 10.1016/j.neunet.2013.03.006 · DOI
- 2014, MATLAB. version 8.3 (R2014a)
Cited by
Sorted by citations
Items 101–130 of 130
Temporal coding enables hyperacuity in event-based vision
Assa, E., Rivkind, A., Kreisserman, M., Khan, F. S., Khan, S. H., & Ahissar, E. (2026) · Nature Communications · doi:10.1038/s41467-026-76878-6 · Cited by 4
“Tiny images constitute a particularly stringent test case in which spatial information alone is insuf fi cient: the object occupies only a few sensor pixels, so fi ne spatial details required to recognize the object are eliminated by sensor pixelation.”
Evaluating Image-Based Face and Eye Tracking with Event Cameras
Iddrisu, K., Shariff, W., O'Connor, N. E., Lemley, J., & Little, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-92460-6_14 · Cited by 2
Dark Photo Reconstruction by Event Camera
Jiang, Z. (2019) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv47840.2019.00027 · Cited by 2
“Barua et al. [3] used a block-based sparse dictionary to perform intensity reconstruction on simulated and real event data in the presence of noise.”
MethodLiu, S., Alexandru, R., & Dragotti, P. L. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746331 · Cited by 2
Krishnan, S., Barua, S., Frankel, T. L., & Rao, A. U. K. (2022) · Physics in Medicine and Biology · doi:10.1088/1361-6560/aca86a · Cited by 3
“…in increasing classification accuracy inmultiple applications for image denoising and classification, and encouraging results have been observed in a variety of use cases (some examples being Aharon et al 2006, Srinivas et al 2013, AlShaikhli et al 2014, Cruz andAlfonso 2015, Barua et al 2016).”
BackgroundSelf-citationSpike-Based Vision for Autonomous Driving Scenarios
Zhang, J., Zheng, Y., Yu, Z., & Huang, T. (2024) · Strategic Study of CAE · doi:10.15302/j-sscae-2024.01.012 · Cited by 2
“L5 级 动态视觉传感器发展较早，研究内容丰富 [11,12] 。 早期的影像重建研究多使用优化 [13,14] 、正则化 [15] 及 时间滤波 [16,17] 等方案，之后深度学习（ DL ）方案占 据主流 [18~28] 。在场景理解任务中，使用动态视觉传 感器解决光流估计或目标跟踪任务有一定天然优 势，事件流的产生往往代表着运动的边缘 [29] ，研究 多基于此展开 [30~36] 。目前也有许多研究针对深度估 计展开以加强对传感器三维场景的理解 [37~56] 。 脉冲相机的采样机制模拟生物视觉感知系统， 其输出数据以脉冲流形式呈现，具有高时域分辨…”
WaveE2VID: Frequency-Aware Event-Based Video Reconstruction
Maqsood, R., Nunes, P. J. L., Conti, C., & Soares, L. D. (2025) · Proceedings - International Conference on Image Processing · doi:10.1109/icip55913.2025.11084548 · Cited by 1
Event-based facial microexpression analysis using Spiking Neural Networks
Mastropasqua, N., Bugueno-Cordova, I. G., Verschae, R., Acevedo, D. G., Negri, P., & Buemi, M. E. (2025) · International Conference on Pattern Recognition Systems (ICPRS) · doi:10.1109/icprs66293.2025.11302823 · Cited by 1
“Well studied problems like face detection, an essential step for many downstream tasks, become non-trivial with event cameras and have received considerable attention in previous work [3], [8].”
Exploring Spatial-Temporal Dynamics in Event-Based Facial Micro-Expression Analysis
Mastropasqua, N., Bugueno-Cordova, I. G., Verschae, R., Acevedo, D. G., Negri, P., & Buemi, M. E. (2025) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw69036.2025.00496 · Cited by 1
“[3] developed a patch-based model capable of reconstructing faces and demonstrated direct face detection from events.”
Reconstructing Intensity Images from Binary Spatial Gradient Cameras
Jayasuriya, S., Gallo, O., Gu, J., Aila, T., & Kautz, J. (2017) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2017.47 · Cited by 1
“did face detection and intensity reconstruction [2], and Kim et al.”
Time encoding and decoding of multidimensional signals with finite rate of innovation
Alexandru, R., & Dragotti, P. L. (2021) · Asilomar Conference on Signals, Systems and Computers (ACSSC) · doi:10.1109/ieeeconf53345.2021.9723165 · Cited by 1
“The recovery of real-time video streams from time-encoded information has recently experienced renewed interest in the neuromorphic engineering community [3], computer vision [4], [6], [7], as well as signal processing [8], [9], [10].”
BackgroundOlay Kamerası ile Verimli Konuşma Sesi Tespiti için Zamansal Evrişimsel Ağlar
Savran, A. (2024) · Journal of Intelligent Systems Theory and Applications · doi:10.38016/jista.1400047 · Cited by 1
Shuming, 杨. Y., Xing, 瞿. Q., & Chunyang, 马. M. (2024) · Acta Optica Sinica (Online) · doi:10.3788/aosol240432 · Cited by 1
Bringing Blurry Alive at High Frame-Rate with an Event Camera.
Pan, L., Hartley, R. I., Scheerlinck, C., Liu, M., Yu, X., & Dai, Y. (2019) · Cited by 1
Address-Event Signal Processing: Silicon Retina, Cochlea and Olfaction A Review
Tayarani, M., & Schmuker, M. (2021) · Cited by 1
Computing Spatial Image Convolutions for Event Cameras.Preprint
Scheerlinck, C., Barnes, N. M., & Mahony, R. E. (2018) · arXiv (Cornell University) · Cited by 1
Adaptive spatio-temporal clustering for small object detection using event-based camera
Sun, Z., Li, M., Lin, Z., Zhang, D., & Deng, X. (2022) · Eighth Symposium on Novel Photoelectronic Detection Technology and Applications · doi:10.1117/12.2623798
“Our work differs from previous efforts (such as the image reconstructing [10] methods) in the following aspects: (I) Our method does not need to know the prior information of the objects, and is flexible and adaptive to different sizes of the small object.”
BackgroundMethodLow-Cost Video Super-Resolution Assisted by Event Signals
Han, Y., Suo, J., & Dai, Q. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-6613-2_637
Faces in Event Streams (FES): An Annotated Face Dataset for Event CamerasPreprint
Bissarinova, U., Rakhimzhanova, T., Kenzhebalin, D., & Varol, H. A. (2023) · doi:10.36227/techrxiv.22826654
Intensity-Image Reconstruction Using Event Camera Data by Changing in LSTM Update
Soltangholi, A. R., Harati, A., & Vahedian, A. (2023) · International Conference on Computer and Knowledge Engineering · doi:10.1109/iccke60553.2023.10326267
“In 2016, Miyatani et al. [5] used a dictionary-based model for image reconstruction and noise reduction, which was based on learning.”
BackgroundComparative Study on Serial and Parallel Implementation of Face Detection
Mallegowda, M., Theertha, K., Varsha, S., & Kanavalli, A. (2024) · International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE) · doi:10.1109/iitcee59897.2024.10467826
Target detection method based on event-time surface feature fusion network
Xu, C., Li, A., Feng, T., Xiang, X., Chen, Y., Cai, Y., Han, Y., & Liu, L. (2025) · doi:10.1117/12.3052785
“In the first category, Barua et al. [4] mapped sparse event information by selecting spatiotemporal windows of event data and applying dictionary learning to infer image gradients.”
Noise Filtering Algorithm for Event Streams Using Spatial and Temporal Correlation
Song, J., Sun, T., Chen, Y., Meng, X., Zhang, A., & Wang, X. (2024) · Academic Conference of China Instrument and Control Society (ACCIS) · doi:10.1109/accis62068.2024.10948724
Review on Event-Based Vision: Data Representation, Image Generation, Calibration and Recognition
Zhang, L., Yang, P., Yang, H., Wang, F., & Zhang, S. (2025) · IEEE International Conference on Unmanned Systems (ICUS) · doi:10.1109/icus66297.2025.11294255
“Some recognition methods convert spikes to frames during inference[81,82], while others convert trained Artificial Neural Networks (ANNs) into Spiking Neural Networks (SNNs) capable of directly processing event data[83].”
Ev2Gray: event-only intensity imaging – occlusion-referenced log-intensity reconstruction
Bäßler, J., Delucchi, A. L., Bäcker, P., & Heizmann, M. (2026) · tm - Technisches Messen · doi:10.1515/teme-2025-0124
“Barua et al. [9] employ dictionary learning to map local event patterns to spatial gradient estimates, which are then integrated to recover intensity images.”
Yuhan, 鲍. B., Jiajun, 翟. Z., Shaohua, 高. G., & Kaiwei, 汪. W. (2026) · Chinese Journal of Lasers · doi:10.3788/cjl251019
Woo, J. H., & Lee, E. (2026) · Applied Sciences · doi:10.3390/app16052430
Event-based Liveness Detection using Temporal Ocular Dynamics: An Exploratory Approach
Mastropasqua, N., Bugueno-Cordova, I. G., Verschae, R., Acevedo, D., & Negri, P. (2026) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg67764.2026.11557041
“Early work in [7] introduced patch-based models, while [27] leveraged blink dynamics for probabilistic face localization and tracking.”
Event‐Based Video Reconstruction via Bidirectional Spatiotemporal Learning
Liu, J., Zhang, C., Lin, M., Gao, C., Wang, H., & Yu, L. (2026) · IET Image Processing · doi:10.1049/ipr2.70474
Metadata
- Authors
- Miyatani, Y., Barua, S., & Veeraraghavan, A.
- Affiliations
- Rice University (US)
- Venue
- 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
- Publisher
- IEEE
- Published
- 2016-03
- Volume
- 2016
- Pages
- 1-9
- ISSN
- 2472-6737 (ISSN-L)
- OpenAlex
- W2403865344
- Cited by
- 133
- References
- 37
- Citations by year
- 2026: 6 · 2025: 16 · 2024: 19 · 2023: 18 · 2022: 8 · 2021: 20 · 2020: 21 · 2019: 18 · 2018: 3 · 2017: 2 · 2016: 2
- FWCI
- 2.89
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Winter Conference on Applications of Computer Vision (publishedVersion)
- IEEE Conference Proceedings
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Keywords
- event cameras, event-based vision, face detection, video reconstruction, high-speed imaging, low-power vision, event stream processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
