Non-homogeneous Content-driven Video-retargeting

By Lior Wolf, Moshe Guttmann, Daniel Cohen-Or. IEEE International Conference on Computer Vision, 2007

528 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/657cf56b8bef745901c535c2730163f25974d51b

How researchers see this paper

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Saliency Detection in the Compressed Domain for Adaptive Image Retargeting (2012, unknown): “Wolf et al. introduced a video retargeting algorithm through introducing a linear system to determine the new pixel position [13].”
Content-preserving warps for 3D video stabilization (2009, background): “…shifts are small, the local deformations induced by the sparse displacements are smaller than for resizing applications [Avidan and Shamir 2007; Wolf et al. 2007], and therefore a local deformation that is nearly a similarity transformation can usually be found without exploiting low-salience…”
Shift-map image editing (2009, methodology): “It is also possible to use automatic saliency map computed from the image such as the ones proposed in [19, 16].”
PatchMatch: a randomized correspondence algorithm for structural image editing (2009, methodology): “For image retargeting, we can easily implement importance masks to specify regions that should not deform at all [Avidan and Shamir 2007; Wolf et al. 2007; Rubinstein et al. 2008; Simakov et al. 2008] or scale uniformly [Wang et al.”
Parallax-Tolerant Image Stitching (2014, methodology): “Various content-preserving warping methods have been used in applications, such as video stabilization [14] and image and video retargeting [25, 24].”
Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks (2018, unknown): “Similarly to our concept, this can be driven by saliency [24] and formulated as an energy minimization [25] or Finite Element Method [26] problem.”
A comparative study of image retargeting (2010, unknown): “Those are: Nonhomogeneous warping ( WARP ) [Wolf et al. 2007], Seam-Carving ( SC ) [Rubinstein et al. 2008], Scale-and-Stretch ( SNS ) [Wang et al. 2008], Multi-operator ( MULTIOP ) [Ru-binstein et al. 2009], Shift-maps ( SM ) [Pritch et al. 2009], Streaming Video ( SV ) [Kr¨ahenb¨uhl et al. 2009],…”
ActionSpotter: Deep Reinforcement Learning Framework for Temporal Action Spotting in Videos (2020, unknown): “Our framework also does not require video-retargeting [22], [23].”