Impresee
@impresee
Followers
129
Following
102
Media
173
Statuses
354
Search bar for marketing and conversion optimization. Extensions for Magento, Shopify, and every other platform.
San Francisco, CA
Joined April 2016
Espectacular #EstudioNube. Felices de colaborar con nuestra búsqueda y selección de productos, deep analytics y acciones para que las tiendas vendan más y mejor, ahora un formato full omnicanal. #busquedainteligente @Tiendanube @Tiendanubemex
0
1
2
¿Aún no lees Revista Bits sobre #InteligenciaArtificial? Te recomendamos esta sección con investigaciones en este ámbito, entre ellas trabajos de los profesores @aidhog, @felipebravom @isipiran @alexbergel @lejyby y @jbarriosx. Descarga la Revista en: https://t.co/YxrtIuMgp6
0
6
4
Next talk, "Neural Algorithmic Sketching" from @PetarV_93: There is much similarity between free hand sketching and algorithmic reasoning, so sketching can serve as a basis for representation learning / algorithmic representations of concepts. 1/2
1
4
34
The 1st Workshop on Sketch-Oriented Deep Learning Workshop @CVPRConf kicked off! I'll attempt to live tweet the workshop. @junyanz89's talk on "Sketch Your Own Models" discuss combining human sketching to interface with the latent space of photos, and even rewrite entire models.
1
8
42
Interested in Deep Learning for Doodles? 🖍️ Excited to announce that our proposal for a @CVPR workshop on “Sketch-Oriented Deep Learning” (SketchDL) has been accepted! The workshop is on June 19, and the submission deadline is March 23. Workshop website: https://t.co/JnaDWTci9I
6
53
322
Graph neural networks demonstrate promising potential for algorithmic reasoning (some early results for extrapolation), and in principle can be trained via backprop to learn drawing algorithms and even parse-tree generative models (i.e. L-Systems representations of plants). 2/2
1
2
36
There are important open challenges in the intersection of ML and cognitive science, with regards to not only object-part segmentation in both photos and human sketches, but also learning higher-order abstractions of images, and linking these to cognitive development. (2/2)
1
7
37
Im2Vec: Synthesizing Vector Graphics without Vector Supervision (also @CVPR 2021 Oral) “Many challenges remain, but sketches and vector graphics data are a good testing ground for learning representations of object composition.” https://t.co/Lmk2HYq1if
https://t.co/dn3YjmLe0r
Im2Vec: Synthesizing Vector Graphics without Vector Supervision Machine learning will soon surpass hand-engineered image vectorization methods (which are already quite good), but will allow us to more interesting things with the learned representations. https://t.co/KEsIYdBSW0
1
7
28
On Training Sketch Recognizers for New Domains They use a Red Alert-like 2D RTS game for sketch-based interaction, and show limitations of traditional deep networks for domain shifts, highlighting the importance of ecological valid datasets for training. https://t.co/qfXM3MlHjo
1
2
15
Engineering Sketch Generation for Computer-Aided Design (Autodesk Research) They look at 2 different generative models: CurveGen (think SVG primatives) and TurtleGen (think Turtle Graphics Logo language from the 1970s), for engineering sketch generation. https://t.co/Rn5gsCoDjC
0
4
30
Sketch-QNet: A Quadruplet ConvNet for Color Sketch-Based Image Retrieval Interesting work to tackle the color sketch-based image retrieval (CSBIR) problem, achieving new SOTA results. Authors are from a startup “Impresee” focused on sketch-based methods. https://t.co/TRaNECS128
1
4
22
Compact and Effective Representations for Sketch-based Image Retrieval They show that UMAP is a great tool for sketch-based image retrieval. I think at some point we should have sketch-based image search engines that work well. https://t.co/4cGQbmHcnu
1
6
26
Esta semana aprendí algo: que si hago las presentaciones de la empresa como hago las charlas, ya me sale todo natural. Lo cuento como gran logro personal, y no se imaginan cuánto me costó llegar a este punto.
4
1
26
Pablo Torres, alumno del @dccuchile, presentando en el workshop SketchDL de la CVPR 2021, la conferencia de computer vision más grande del mundo. Trabajo conjunto con @jmsaavedrar de @impresee. Empresas chilenas y universidades colaborando en ciencia de nivel mundial.
0
2
5
Aníbal Fuentes de @impresee, presentando en el workshop SketchDL de la CVPR 2021, la conferencia científica más grande del mundo de computer vision. Trabajo conjunto con @jmsaavedrar. ¿Quién dice que no se puede hacer ciencia de nivel mundial en las empresas chilenas?
0
3
8
Google will stop using 3rd-party tracking cookies on its Chrome browser! At #Impresee we gather useful data for #eCommerce while respecting visitors' privacy. This change won't affect our analytics systems. We're convinced this is great news. What do you think?
1
1
2
Investigaciones de los estudiantes del #DCCUChile Pablo Torres y Andrés Baloian fueron aceptadas en workshops de la International Conference on Computer Vision (@CVPR). Ambos trabajos fueron guiados por el profesor part-time José M. Saavedra. Noticia en: https://t.co/V78bPckDFx
1
3
13
El valor de las barras de búsquedas avanzadas es que juegan un rol de asesor de ventas personalizado para tus visitantes y lo mejor de todo es que te notifica sobre lo que están pidiendo tus visitantes y cómo lo están pidiendo. - @impresee
https://t.co/A10dro1xhj
es.jumpseller.com
Hay mucha información que puedes obter desde tu barra de búsqueda, pero geralmente esos datos no son recogidos. Aprende como empezar a coletar e aplicar estes datos en acciones para tu negocio en...
2
3
3