Despite its empirical success, the theoretical foundations of self-supervised contrastive learning (CL) are not yet fully established. In this work, we address this gap by showing that standard CL objectives implicitly approximate a supervised variant we call the negatives-only supervised contrastive loss (NSCL), which excludes same-class contrasts. We prove that the gap between the CL and NSCL losses vanishes as the number of semantic classes increases, under a bound that is both label-agnostic and architecture-independent. We characterize the geometric structure of the global minimizers of the NSCL loss: the learned representations exhibit augmentation collapse, within-class collapse, and class centers that form a simplex equiangular tight frame. We further introduce a new bound on the few-shot error of linear-probing. This bound depends on two measures of feature variability—within-class dispersion and variation along the line between class centers. We show that directional variation dominates the bound and that the within-class dispersion's effect diminishes as the number of labeled samples increases. These properties enable CL and NSCL-trained representations to support accurate few-shot label recovery using simple linear probes. Finally, we empirically validate our theoretical findings: the gap between CL and NSCL losses decays at a rate of $\mathcal{O}(\frac{1}{\#\text{classes}})$; the two losses are highly correlated; minimizing the CL loss implicitly brings the NSCL loss close to the value achieved by direct minimization; and the proposed few-shot error bound provides a tight estimate of probing performance in practice.

In this work, we present a method to address the problem of novel view and time synthesis of complex dynamic scenes considering the input video is subject to blurriness caused due to camera or object motion or out-of-focus blur. Neural Scene Flow Field (NSFF) has shown remarkable results by training a dynamic NeRF to capture motion in the scene, but this method is not robust to unstable camera handling which can lead to blurred renderings. We propose Deblur-NSFF, a method that learns spatially-varying blur kernels to simulate the blurring process and gradually learns a sharp time-conditioned NeRF representation. We describe how to optimize our representation for sharp space-time view synthesis. Given blurry input frames, we perform both quantitative and qualitative comparison with state-of-the-art methods on modified NVIDIA Dynamic Scene dataset. We also compare our method with Deblur-NeRF, a method that has been designed to handle blur in static scenes. The demonstrated results show that our method outperforms prior work.

Learning to recover clear images from images having a combination of degrading factors is a challenging task. That being said, autonomous surveillance in low visibility conditions caused by high pollution/smoke, poor air quality index, low light, atmospheric scattering, and haze during a blizzard, etc, becomes even more important to prevent accidents. It is thus crucial to form a solution that can not only result in a high-quality image but also which is efficient enough to be deployed for everyday use. However, the lack of proper datasets available to tackle this task limits the performance of the previous methods proposed. To this end, we generate the LowVis-AFO dataset, containing 3647 paired dark-hazy and clear images. We also introduce a new lightweight deep learning model called Low-Visibility Restoration Network (LVRNet). It outperforms previous image restoration methods with low latency, achieving a PSNR value of 25.744 and an SSIM of 0.905, hence making our approach scalable and ready for practical use.

Drone-camera based human activity recognition (HAR) has received significant attention from the computer vision research community in the past few years. A robust and efficient HAR system has a pivotal role in fields like video surveillance, crowd behavior analysis, sports analysis, and human-computer interaction. What makes it challenging are the complex poses, understanding different viewpoints, and the environmental scenarios where the action is taking place. To address such complexities, in this paper, we propose a novel Sparse Weighted Temporal Attention (SWTA) module to utilize sparsely sampled video frames for obtaining global weighted temporal attention. The proposed SWTA is divided into two components. First, temporal segment network that sparsely samples a given set of frames. Second, weighted temporal attention, which incorporates a fusion of attention maps derived from optical flow, with raw RGB images. This is followed by a basenet network, which comprises a convolutional neural network (CNN) module along with fully connected layers that provide us with activity recognition. The SWTA network can be used as a plug-in module to the existing deep CNN architectures, for optimizing them to learn temporal information by eliminating the need for a separate temporal stream. It has been evaluated on three publicly available benchmark datasets, namely Okutama, MOD20, and Drone-Action. The proposed model has received an accuracy of 72.76%, 92.56%, and 78.86% on the respective datasets thereby surpassing the previous state-of-the-art performances by a margin of 25.26%, 18.56%, and 2.94%, respectively.

We introduce Amazon Berkeley Objects (ABO), a new large-scale dataset designed to help bridge the gap between real and virtual 3D worlds. ABO contains product catalog images, metadata, and artist-created 3D models with com-plex geometries and physically-based materials that cor-respond to real, household objects. We derive challenging benchmarks that exploit the unique properties of ABO and measure the current limits of the state-of-the-art on three open problems for real-world 3D object understanding: single-view 3D reconstruction, material estimation, and cross-domain multi-view object retrieval.

A robust and efficient crowd counting framework forms a vital step towards the analysis of a crowded scene and finds its applications in social distance monitoring, traffic management, and video surveillance. We argue that visible RGB images fail to yield high-quality density maps owing to poor lighting conditions during the dark when an anomaly is more likely to occur. To tackle this scenario, we introduce a novel architecture Toggle-Fusion Network (TFNet) that effectively utilises a multimodal dataset, RGBT-CC, containing pairs of thermal and RGB images. Our approach eliminates the need for two branches for each of these modalities as proposed in the baseline by conditionally fusing the thermal and RGB images with the help of a toggle, saliency maps, and a rolling guidance filter. We conduct extensive experiments and delineate the importance of individual components of our method in the ablation study. TFNet, after evaluation on RGBT-CC, receives an RMSE value of 6.11 thereby establishing new state-of-the-art for the dataset. The code is made publicly available https://github.com/ShreyasSR/TFNet