We introduce point affiliation into feature upsampling, a notion that describes the affiliation of each upsampled point to a semantic cluster formed by local decoder feature points with semantic similarity. By rethinking point affiliation, we present a generic formulation for generating upsampling kernels. The kernels encourage not only semantic smoothness but also boundary sharpness in the upsampled feature maps. Such properties are particularly useful for some dense prediction tasks such as semantic segmentation. The key idea of our formulation is to generate similarity-aware kernels by comparing the similarity between each encoder feature point and the spatially associated local region of decoder features. In this way, the encoder feature point can function as a cue to inform the semantic cluster of upsampled feature points. To embody the formulation, we further instantiate a lightweight upsampling operator, termed Similarity-Aware Point Affiliation (SAPA), and investigate its variants. SAPA invites consistent performance improvements on a number of dense prediction tasks, including semantic segmentation, object detection, depth estimation, and image matting. Code is available at: https://github.com/poppinace/sapa

Game Theory: Could geopolitics impact the business of sport in the Gulf? The Gulf helped transform global sport through billions in investment. But as geopolitical tensions rise is that era of rapid expansion coming to an end? Al Jazeera's Samantha Johnson looks at how geopolitics could impact the business of sport. The Masters: Golf's segregated past Are Iran's athletes political pawns?

Kenya's Sabastian Sawe has become the first man to run a marathon in under two hours, winning the London Marathon in 1:59:30. Ethiopia's Tigst Assefa defended her London Marathon crown on Sunday, breaking her own world record. The 31-year-old, who has never lost a marathon, smashed the world record by 65 seconds. Yomif Kejelcha of Ethiopia stayed on Sawe's heels for most of the 42.195km course before fading down the final stretch to take second in his marathon debut with 1:59:41, while Jacob Kiplimo of Uganda won bronze in 2:02:28. All three finished under Kiptum's previous record time.

We propose a novel neural network-based approach to modeling protein dynamics using an implicit representation of a protein's surface in 3D and time. Our method utilizes the zero-level set of signed distance functions (SDFs) to represent protein surfaces, enabling temporally and spatially continuous representations of protein dynamics. Our experimental results demonstrate that our model accurately captures protein dynamic trajectories and can interpolate and extrapolate in 3D and time. Importantly, this is the first study to introduce this method and successfully model large-scale protein dynamics. This approach offers a promising alternative to current methods, overcoming the limitations of first-principles-based and deep learning methods, and provides a more scalable and efficient approach to modeling protein dynamics. Additionally, our surface representation approach simplifies calculations and allows identifying movement trends and amplitudes of protein domains, making it a useful tool for protein dynamics research. Codes are available at https://github.com/Sundw-818/DSR,

What are Russia's gains from the Iran war? 'We are not losers; we are winners' Ukrainian officials say Russian attacks in several regions have killed at least five people and damaged a ship in the port of Odesa - as Moscow claimed to have intercepted more than 200 Ukrainian drones. A Russian drone attack killed two men on Saturday in Ukraine's northeastern Sumy region, according to Governor Oleh Hryhorov. He said civilians were hit in Bilopil close to the Russian border. In the southern region of Kherson, Governor Oleksandr Prokudin said Russian shelling wounded seven people. Further east, Russian forces launched more than 700 attacks on 50 settlements in the Zaporizhia region over the past 24 hours, killing two people and injuring four, according to Governor Ivan Fedorov.

Capturing accurate uncertainty quantification of the predictions from deep neural networks is important in many real-world decision-making applications. A reliable predictor is expected to be accurate when it is confident about its predictions and indicate high uncertainty when it is likely to be inaccurate. However, modern neural networks have been found to be poorly calibrated, primarily in the direction of overconfidence. In recent years, there is a surge of research on model calibration by leveraging implicit or explicit regularization techniques during training, which achieve well calibration performance by avoiding overconfident outputs. In our study, we empirically found that despite the predictions obtained from these regularized models are better calibrated, they suffer from not being as calibratable, namely, it is harder to further calibrate these predictions with post-hoc calibration methods like temperature scaling and histogram binning. We conduct a series of empirical studies showing that overconfidence may not hurt final calibration performance if post-hoc calibration is allowed, rather, the penalty of confident outputs will compress the room of potential improvement in post-hoc calibration phase. Our experimental findings point out a new direction to improve calibration of DNNs by considering main training and post-hoc calibration as a unified framework.

Monocular 3D detection of vehicle and infrastructure sides are two important topics in autonomous driving. Due to diverse sensor installations and focal lengths, researchers are faced with the challenge of constructing algorithms for the two topics based on different prior knowledge. In this paper, by taking into account the diversity of pitch angles and focal lengths, we propose a unified optimization target named normalized depth, which realizes the unification of 3D detection problems for the two sides. Furthermore, to enhance the accuracy of monocular 3D detection, 3D normalized cube depth of obstacle is developed to promote the learning of depth information. We posit that the richness of depth clues is a pivotal factor impacting the detection performance on both the vehicle and infrastructure sides. A richer set of depth clues facilitates the model to learn better spatial knowledge, and the 3D normalized cube depth offers sufficient depth clues. Extensive experiments demonstrate the effectiveness of our approach. Without introducing any extra information, our method, named MonoUNI, achieves state-of-the-art performance on five widely used monocular 3D detection benchmarks, including Rope3D and DAIR-V2X-I for the infrastructure side, KITTI and Waymo for the vehicle side, and nuScenes for the cross-dataset evaluation.