Tootfinder

Reconstructing Hand-Held Objects in 3D
Jane Wu, Georgios Pavlakos, Georgia Gkioxari, Jitendra Malik
https://arxiv.org/abs/2404.06507 https://

Reconstructing Hand-Held Objects in 3D
Objects manipulated by the hand (i.e., manipulanda) are particularly challenging to reconstruct from in-the-wild RGB images or videos. Not only does the hand occlude much of the object, but also the object is often only visible in a small number of image pixels. At the same time, two strong anchors emerge in this setting: (1) estimated 3D hands help disambiguate the location and scale of the object, and (2) the set of manipulanda is small relative to all possible objects. With these insights in…

The House Rules Committee's schedule for next week consists entirely of a half dozen bills to 😮prohibit the Energy Department from setting energy use standards for home appliances.😮
The Liberty in Laundry Act, the Refrigerator Freedom Act and the Stop Unaffordable Dishwasher Standards, or SUDS, Act😂 are among the bills.
There is no sign, however, of legislation to provide military aid to 🇺🇦Ukraine, 🇮🇱Israel or 🇹🇼Taiwan, which some lawmakers have said they expect to come up…

House Republicans fume over "messaging" votes
"Those post offices aren't going to name themselves," a conservative lawmaker quipped.

ViboPneumo: A Vibratory-Pneumatic Finger-Worn Haptic Device for Altering Perceived Texture Roughness in Mixed Reality
Shaoyu Cai, Zhenlin Chen, Haichen Gao, Ya Huang, Qi Zhang, Xinge Yu, Kening Zhu
https://arxiv.org/abs/2403.05182

ViboPneumo: A Vibratory-Pneumatic Finger-Worn Haptic Device for Altering Perceived Texture Roughness in Mixed Reality
Extensive research has been done in haptic feedback for texture simulation in virtual reality (VR). However, it is challenging to modify the perceived tactile texture of existing physical objects which usually serve as anchors for virtual objects in mixed reality (MR). In this paper, we present ViboPneumo, a finger-worn haptic device that uses vibratory-pneumatic feedback to modulate (i.e., increase and decrease) the perceived roughness of the material surface contacted by the user's fingerpad …

This https://arxiv.org/abs/2404.06479 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

Text-Based Reasoning About Vector Graphics
While large multimodal models excel in broad vision-language benchmarks, they often struggle with tasks requiring precise perception of low-level visual details, such as comparing line lengths or solving simple mazes. In particular, this failure mode persists in question-answering tasks about vector graphics -- images composed purely of 2D objects and shapes. To address this challenge, we propose the Visually Descriptive Language Model (VDLM), which performs text-based reasoning about vector gr…

Trent Sieg takes victory lap after becoming Cowboys’ first free agency signing https://www.yardbarker.com/nfl/articles/trent_sieg_takes_victory_lap_after_becoming_cowboys_first_free_agency_signing/s1…

Trent Sieg takes victory lap after becoming Cowboys’ first free agency signing
After becoming the Cowboys‘ first free agency signing of the offseason, long snapper Trent Sieg took a victory lap on social media with a hilarious Eminem-themed video. The video he posted on X includes the tune ‘Without Me’ by Eminem and features his special teams mates, punter Bryan Anger and kicker Brandon Aubrey. In the video, Sieg’s head is superimposed on the rap star’s face. “Everybody, Just follow me!” Sieg wrote on X. The Cowboys are holding on to the veteran long snapp…

Raiders Adding Competition For Quarterback Aidan O’Connell https://www.yardbarker.com/nfl/articles/raiders_adding_competition_for_quarterback_aidan_oconnell/s1_17150_40092905

Raiders Adding Competition For Quarterback Aidan O’Connell
One of the biggest question marks the Las Vegas Raiders have coming into the 2024 offseason is what to do at quarterback. The team decided to move on from veteran Jimmy Garoppolo during the 2023 season when interim head coach Antonio Pierce opted to bench him for rookie Aidan O’Connell. With Pierce now taking the head coaching role full-time, he has to answer questions about quarterback once again. Will O’Connell, who showed some signs during his rookie season, be their starter in 2024? Or …

Congressional offices are being flooded with calls from angry constituents following TikTok's push notification asking users to call their representatives (Axios)
https://www.axios.com/2024/03/07/tiktok-ban-congress-phone-calls

Furious Congress plows forward with TikTok bill after user revolt
"So bad we turned phones off."

Sorry, Zoomers, it's not us, it's you.
https://www.theguardian.com/music/2024/mar/29/song-lyrics-getting-simpler-more-repetitive-angry-and-self-obsessed-study

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
Chun-Peng Chang, Shaoxiang Wang, Alain Pagani, Didier Stricker
https://arxiv.org/abs/2403.03077

MiKASA: Multi-Key-Anchor & Scene-Aware Transformer for 3D Visual Grounding
3D visual grounding involves matching natural language descriptions with their corresponding objects in 3D spaces. Existing methods often face challenges with accuracy in object recognition and struggle in interpreting complex linguistic queries, particularly with descriptions that involve multiple anchors or are view-dependent. In response, we present the MiKASA (Multi-Key-Anchor Scene-Aware) Transformer. Our novel end-to-end trained model integrates a self-attention-based scene-aware object e…

Text-Based Reasoning About Vector Graphics
Zhenhailong Wang, Joy Hsu, Xingyao Wang, Kuan-Hao Huang, Manling Li, Jiajun Wu, Heng Ji
https://arxiv.org/abs/2404.06479

Text-Based Reasoning About Vector Graphics
While large multimodal models excel in broad vision-language benchmarks, they often struggle with tasks requiring precise perception of low-level visual details, such as comparing line lengths or solving simple mazes. In particular, this failure mode persists in question-answering tasks about vector graphics -- images composed purely of 2D objects and shapes. To address this challenge, we propose the Visually Descriptive Language Model (VDLM), which performs text-based reasoning about vector gr…