Data & Code

Dataset

  • LuNoTim-CT

Description:

Our LuNoTim-CT dataset is generated based on the LIDC-IDRI dataset [1], which contains 1,020 lung CT scans with 883 of them having lung nodules. The CTs in our dataset are tampered by three different tampering methods including copy-move, classical inpainting, and deep inpainting by removing and adding nodules from/to the original CT scans in the original LIDC-IDRI dataset.

Download: Version 1.0

Contact: (questions/error reports) Longlong Jing

  • ASL-100-RGBD Dataset

Description:

A new dataset has been collected for this research in collaboration with ASL computational linguistic researchers, from native ASL signers (individuals who have been using the language since very early childhood) who performed a word list of 100 ASL signs by using a Kinect V2 camera. Participants responded affirmatively to the following screening question: Did you use ASL at home growing up, or did you attend a school as a very young child where you used ASL? Participants were provided with a slide-show presentation that asked them to perform a sequence of 100 individual ASL signs, without lowering their hands between words. Since this new dataset includes 100 signs with RGB and depth data, we refer to it as the ASL-100-RGBD dataset. There is a total of 42 videos recorded from 22 participants each performing 100 ASL signs. Each video includes 4 channels: RGB, Skeleton, Depth and HDface recorded by Kinect V2 camera. The following video is one performance among 42 videos. We merged all channels (RGB, Depth, Skeleton and HDface) of this video into one single video for a better demonstration. The upper-left window shows the RGB chennel, the upper-right frames window shows the Skeleton joints which including 25 body joints (overlaid on RGB frames for visualization purpose), the lower-left window shows the Depth channel, and the lower-right window illustrates the HDface channel which including 1,347 points. The Kinect V2 has RGB image resolution of 1920 x 1080 pixels (same for Skeleton and HDface channels) and Depth image resolution of 512 x 424. All channels (RGB, Depth, Skeleton and HDface) are resized to 480 * 270 in this example video for visualization.

Download: Version 1.0

Contact: (questions/error reports) Longlong Jing

  • Flow Super-Resolution Dataset (ISPRS)

The dataset accompanies the paper:

Z. Petrou, Y. Xian, and Y. Tian, Towards Breaking the Spatial Resolution Barriers: An Optical Flow and Super-Resolution Approach for Sea Ice Motion Estimation, ISPRS Journal of Photogrammetry and Remote Sensing, Accepted, 2018.

Download: Version 1.0

Contact: (questions/error reports) Zisis I. Petrou

  • Barcode Dataset (IEEE-CYBER 2017)

The dataset accompanies the paper:

W. Fernandez, Y. Xian, and Y. Tian, Image-Based Barcode Detection and Recognition to Assist Visually Impaired Persons, IEEE Int. Conf. on CYBER Technology in Automation, Control, and Intelligent Systems (IEEE-CYBER), 2017.

Download: Version 1.0

Contact: (questions/error reports) Yang Xian

  • Traffice Guide Panel Text Dataset (ECCVw 2016)

The dataset accompanies the paper:

X. Rong, C. Yi, and Y. Tian. Recognizing Text-based Traffic Guide Panels with Cascaded Localization Network. ECCV Workshop on Computer Vision for Road Scene Understanding and Autonomous Driving (CVRSUAD), 2016.

Download: Version 1.0

Contact: (questions/error reports) Xuejian Rong

  • RGB-D Staircase Detection Dataset (MMC 2016)

The dataset accompanies the paper:

R. Munoz, X. Rong, and Y. Tian. Depth-aware Indoor Staircase Detection and Recognition for the Visually Impaired. ICME Workshop on Mobile Multimedia Computing (MMC), 2016.

Download: Version 1.0

Contact: (questions/error reports) Xuejian Rong

  • MODIS Sea Ice Motion Estimation Dataset (TGRS 2017)

The dataset accompanies the paper:

Z. I. Petrou and Y. Tian, “High resolution sea ice motion estimation with optical flow using satellite spectroradiometer data,” IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 3, pp. 1339–1350, March 2017.

Download: Version 1.0

Contact: (questions/error reports) Zisis I. Petrou

  • AMSR2 Super-Resolution Dataset (TGRS 2017)

The dataset accompanies the paper:

Y. Xian, Z. I. Petrou, Y. Tian, and W. N. Meier, “Super-resolved fine scale sea ice motion tracking,” IEEE Transactions on Geoscience and Remote Sensing, vol. 55, no. 8, August 2017. DOI: 10.1109/TGRS.2017.2699081

Download: Version 1.0

Contact: (questions/error reports) Yang Xian

  • CCNY Cell2Ear Detection Dataset (TRECVID 2014)

The dataset accompanies the paper:

Yang. Xian, X. Rong, X. Yang, and Y. Tian. CCNY at TRECVID 2014: Surveillance Event Detection. NIST TREC Video Retrieval Evaluation (TRECVID) Workshop, 2014.

Download: Version 1.0

Contact: (questions/error reports) Xuejian Rong

  • Orient Scene Text Dataset (CVIU 2012)

The dataset accompanies the paper:

C. Yi and Y. Tian. Text Extraction from Scene Images by Character Apperance and Structure Modeling. In Computer Vision and Image Understanding, Vol. 117, No. 2, pp. 182-194, 2013.

Download: Version 1.1, Project Page

Contact: (questions/error reports) Chucai Yi

  • Spatial Hot Maps (TRECVID 2012)

The dataset accompanies the paper:

X. Yang, C. Yi, L. Cao, and Y. Tian. MediaCCNY at TRECVID 2012: Surveillance Event Detection. NIST Workshop on TREC Video Retrieval Evaluation (TRECVID), 2012.

Download: Version 1.0 (November 5, 2012)

Contact: (questions/bug reports) Xiaodong Yang

  • CCNY Clothing Pattern Dataset (ACM MM 2011)

The dataset accompanies the paper:

X. Yang, S. Yuan, and Y. Tian. Recognizing Clothes Patterns for Blind People by Confidence Margin based Feature Combination. ACM Multimedia (MM), 2011.

Download: Version 1.2

Contact: (questions/error reports) Xiaodong Yang

  • Door Detection Dataset (ACM MM 2010)

The dataset accompanies the paper:

X. Yang, Y. Tian, C. Yi, and A. Arditi. Context-based Indoor Object Detection as an Aid to Blind Persons Accessing Unfamiliar Environments. ACM Multimedia (MM), 2010.

Download: Version 1.0

Contact: (questions/error reports) Xiaodong Yang

Code

  • Super Sparse Coding Vector (ECCV 2014)

The code package accompanies the paper:

X. Yang and Y. Tian. Action Recognition Using Super Sparse Coding Vector with Spatio-Temporal Awareness. European Conference on Computer Vision (ECCV), 2014.

Download: Version 1.3 (January 25, 2015), Github Project

Contact: (questions/bug reports) Xiaodong Yang

  • Super Normal Vector (CVPR 2014)

The code package accompanies the paper:

X. Yang and Y. Tian. Super Normal Vector for Activity Recognition Using Depth Sequences. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.

Download: Version 1.1 (May 11, 2014), Github Project

Contact: (questions/bug reports) Xiaodong Yang

  • Scene Text Detection (TIP 2012)

The code package accompanies the paper:

C. Yi and Y. Tian. Text String Detection from Natural Scenes by Structure-based Partition and Grouping. In IEEE Transactions on Image Processing, Vol. 21, No. 9, 2012.

Download: Version 1.2 (July 25, 2013), Project Page

Contact: (questions/bug reports) Chucai Yi

  • Daily Living Activity Recognition (IJCVIP 2012)

The code package accompanies the paper:

C. Zhang, and Y. Tian. RGB-D Camera-based Daily Living Activity Recognition. International Journal of Computer Vision and Image Processing (IJCVIP), Vol. 2, No. 4, December 2012.

Download: Version 1.2 (December 22, 2012), Data

Contact: (questions/bug reports) Chenyang Zhang

  • Cascade SVMs (TRECVID 2012)

The code package accompanies the paper:

X. Yang, C. Yi, L. Cao, and Y. Tian. MediaCCNY at TRECVID 2012: Surveillance Event Detection. NIST Workshop on TREC Video Retrieval Evaluation (TRECVID), 2012.

Download: Version 1.5 (November 18, 2012), Project Page

Contact: (questions/bug reports) Xiaodong Yang