Some random links to saliency and visual attention:
- Bottom-Up Visual Attention Home Page, jointly supported by ilab, led by Laurent Itti, and klab, led by Christof Koch.
- A Model of Saliency-Based Visual Attention for Rapid Scene Analysis, by Laurent Itti, Christof Koch, and Ernst Niebur, in TPAMI 1998.
- Saliency Detection: A Spectral Residual Approach, in CVPR 2007.
- Global Contrast based Salient Region Detection, in CVPR 2011.
How to send and reply to email, a blog post by Matt Might. He has another post, not a new one but worth reading again, titled “A thesis proposal is a contract“.
Some recent work on saliency detection on FPGA:
ViSP Visual Servoing Platform, from IRISA.
Kinematics, pattern recognition, and motion control of mask–panel alignment system (non-doi link), to appear in Control Engineering Practice.
The NANOMEFOS non-contact measurement machine for freeform optics (non-doi link), by Rens Henselmans, et al., to appear in Precision Engineering. The PhD thesis of Rens Henselmans is “Non-contact measurement machine for freeform optics“. A demo video is available on the NANOMEFOS page at TNO.
Multi-probe scanning system comprising three laser interferometers and one autocollimator for measuring flat bar mirror profile with nanometer accuracy, to appear in Precision Engineering.
Designing Power and Performance Optimal Application-Specific Network-on-Chip Architectures, to appear in j.micpro.
The Instruction-Set Extension Problem: A Survey, in TRETS May 2011.
Some interesting papers in TPAMI July 2011:
The Journal of Selected Topics in Signal Processing June 2011 is a special issue on Advances in Remote Sensing Image Processing.
What an ISCA! Every paper is of high quality. A few related papers:
- Exploring the Tradeoffs between Programmability and Efficiency in Data-Parallel Accelerators, from ParLab and Cornell. It has a thorough comparison between several parallel architecture templates.
- Energy-efficient Mechanisms for Managing Thread Context in Throughput Processors, from U Texas, Illinois, NVIDIA (Erik Lindholm and William J. Dally), and U Virginia(Kevin Skadron).
- Dark Silicon and the End of Multicore Scaling, from U Washington, Wisc, U Texas, and Microsoft.
- OUTRIDER: Efficient Memory Latency Tolerance with Decoupled Strands, from the Rigel group in Illinois.
- Moguls: a Model to Explore Memory Hierarchy for Throughput Computing, from Penn State U and Intel.
- Kilo-NOC: A Heterogeneous Network-on-Chip Architecture for Scalability and Service Guarantees , from U Texas, NVIDIA, and Carnegie Mellon(Onur Mutlu).
A virtual closed loop method for closed loop identification, to appear in Automatica. (non-doi link)
Energy-Efficient Floating Point Unit Design, in Transactions on Computers July 2011. The floating point operation itself is consuming less energy than moving the data to the floating point unit from the L1 cache.
Some interesting articles in Communications of the ACM June 2011:
EoSens 3CL High-Speed CMOS Camera from Menzel Vision & Robotics is capable of streaming a Region of Interest (ROI) 320×240 at 9797 frames per second (fps). It can reach 285000 fps for lower resolution. It is not an in-situ camera, which only buffers the frames for later readout. It can stream out the frames continuously, if the frame grabber and the processing system can support such high bandwidth. This camera is current available in the Netherlands via Data Vision (datvision.com).
I have just installed Fedora 15 on my laptop. The Gnome 3 is much cleaner than the Gnome 2.