BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Lars Petersson

Lars Petersson contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Computer VisionMachine Learningeess.IVGraphicsHuman-Computer InteractionMultimedia

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
13works
0followers
6topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

13 published item(s)

preprint2026arXiv

SteerSeg: Attention Steering for Reasoning Video Segmentation

Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models (LVLMs) by extracting attention maps and using them as spatial priors for segmentation, enabling training-free grounding. However, these attention maps are optimized for text generation rather than spatial localization, often resulting in diffuse and ambiguous grounding signals. In this work, we introduce SteerSeg, a lightweight framework that identifies attention misalignment as the key bottleneck in attention-based grounding and proposes to steer attention at its source through input-level conditioning. SteerSeg combines learnable soft prompts with reasoning-guided Chain-of-Thought (CoT) prompting. The soft prompts reshape the attention distribution to produce more spatially concentrated maps, while CoT-derived attributes resolve ambiguity among similar objects by guiding attention toward the correct instance. The resulting attention maps are converted into point prompts across keyframes to guide a segmentation model, while candidate tracklets are ranked and selected using correlation-based scoring. Our approach freezes the LVLM and segmentation model parameters and learns only a small set of soft prompts, preserving the model's pretrained reasoning capabilities while significantly improving grounding. Despite being trained only on Ref-YouTube-VOS, SteerSeg generalizes well across diverse benchmarks, significantly improving the spatial grounding capability of LVLMs. Project page: https://steerseg.github.io

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Blind Image Decomposition

We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown. For example, rain may consist of multiple components, such as rain streaks, raindrops, snow, and haze. Rainy images can be treated as an arbitrary combination of these components, some of them or all of them. How to decompose superimposed images, like rainy images, into distinct source components is a crucial step toward real-world vision systems. To facilitate research on this new task, we construct multiple benchmark datasets, including mixed image decomposition across multiple domains, real-scenario deraining, and joint shadow/reflection/watermark removal. Moreover, we propose a simple yet general Blind Image Decomposition Network (BIDeN) to serve as a strong baseline for future work. Experimental results demonstrate the tenability of our benchmarks and the effectiveness of BIDeN.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping

We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution. Unlike single random cropping, which may inadvertently capture only limited information, or irrelevant information, like pure background, unrelated objects, etc, we crop an image multiple times using distinct crop scales, thereby ensuring that multi-scale information is captured. The new input distribution, serving as training data, useful for a number of vision tasks, is then formed by simply mixing multiple cropped views. We first demonstrate that CropMix can be seamlessly applied to virtually any training recipe and neural network architecture performing classification tasks. CropMix is shown to improve the performance of image classifiers on several benchmark tasks across-the-board without sacrificing computational simplicity and efficiency. Moreover, we show that CropMix is of benefit to both contrastive learning and masked image modeling towards more powerful representations, where preferable results are achieved when learned representations are transferred to downstream tasks. Code is available at GitHub.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Curved Geometric Networks for Visual Anomaly Recognition

Learning a latent embedding to understand the underlying nature of data distribution is often formulated in Euclidean spaces with zero curvature. However, the success of the geometry constraints, posed in the embedding space, indicates that curved spaces might encode more structural information, leading to better discriminative power and hence richer representations. In this work, we investigate benefits of the curved space for analyzing anomalies or out-of-distribution objects in data. This is achieved by considering embeddings via three geometry constraints, namely, spherical geometry (with positive curvature), hyperbolic geometry (with negative curvature) or mixed geometry (with both positive and negative curvatures). Three geometric constraints can be chosen interchangeably in a unified design given the task at hand. Tailored for the embeddings in the curved space, we also formulate functions to compute the anomaly score. Two types of geometric modules (i.e., Geometric-in-One and Geometric-in-Two models) are proposed to plug in the original Euclidean classifier, and anomaly scores are computed from the curved embeddings. We evaluate the resulting designs under a diverse set of visual recognition scenarios, including image detection (multi-class OOD detection and one-class anomaly detection) and segmentation (multi-class anomaly segmentation and one-class anomaly segmentation). The empirical results show the effectiveness of our proposal through the consistent improvement over various scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Deep Optimal Embeddings with Sinkhorn Divergences

Deep Metric Learning algorithms aim to learn an efficient embedding space to preserve the similarity relationships among the input data. Whilst these algorithms have achieved significant performance gains across a wide plethora of tasks, they have also failed to consider and increase comprehensive similarity constraints; thus learning a sub-optimal metric in the embedding space. Moreover, up until now; there have been few studies with respect to their performance in the presence of noisy labels. Here, we address the concern of learning a discriminative deep embedding space by designing a novel, yet effective Deep Class-wise Discrepancy Loss (DCDL) function that segregates the underlying similarity distributions (thus introducing class-wise discrepancy) of the embedding points between each and every class. Our empirical results across three standard image classification datasets and two fine-grained image recognition datasets in the presence and absence of noise clearly demonstrate the need for incorporating such class-wise similarity relationships along with traditional algorithms while learning a discriminative embedding space.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Dense Correspondence from Synthetic Environments

Estimation of human shape and pose from a single image is a challenging task. It is an even more difficult problem to map the identified human shape onto a 3D human model. Existing methods map manually labelled human pixels in real 2D images onto the 3D surface, which is prone to human error, and the sparsity of available annotated data often leads to sub-optimal results. We propose to solve the problem of data scarcity by training 2D-3D human mapping algorithms using automatically generated synthetic data for which exact and dense 2D-3D correspondence is known. Such a learning strategy using synthetic environments has a high generalisation potential towards real-world data. Using different camera parameter variations, background and lighting settings, we created precise ground truth data that constitutes a wider distribution. We evaluate the performance of models trained on synthetic using the COCO dataset and validation framework. Results show that training 2D-3D mapping network models on synthetic data is a viable alternative to using real data.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Pyramidal Attention for Saliency Detection

Salient object detection (SOD) extracts meaningful contents from an input image. RGB-based SOD methods lack the complementary depth clues; hence, providing limited performance for complex scenarios. Similarly, RGB-D models process RGB and depth inputs, but the depth data availability during testing may hinder the model's practical applicability. This paper exploits only RGB images, estimates depth from RGB, and leverages the intermediate depth features. We employ a pyramidal attention structure to extract multi-level convolutional-transformer features to process initial stage representations and further enhance the subsequent ones. At each stage, the backbone transformer model produces global receptive fields and computing in parallel to attain fine-grained global predictions refined by our residual convolutional attention decoder for optimal saliency prediction. We report significantly improved performance against 21 and 40 state-of-the-art SOD methods on eight RGB and RGB-D datasets, respectively. Consequently, we present a new SOD perspective of generating RGB-D SOD without acquiring depth data during training and testing and assist RGB methods with depth clues for improved performance. The code and trained models are available at https://github.com/tanveer-hussain/EfficientSOD2

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Towards Open-Set Object Detection and Discovery

With the human pursuit of knowledge, open-set object detection (OSOD) has been designed to identify unknown objects in a dynamic world. However, an issue with the current setting is that all the predicted unknown objects share the same category as "unknown", which require incremental learning via a human-in-the-loop approach to label novel classes. In order to address this problem, we present a new task, namely Open-Set Object Detection and Discovery (OSODD). This new task aims to extend the ability of open-set object detectors to further discover the categories of unknown objects based on their visual appearance without human effort. We propose a two-stage method that first uses an open-set object detector to predict both known and unknown objects. Then, we study the representation of predicted objects in an unsupervised manner and discover new categories from the set of unknown objects. With this method, a detector is able to detect objects belonging to known classes and define novel categories for objects of unknown classes with minimal supervision. We show the performance of our model on the MS-COCO dataset under a thorough evaluation protocol. We hope that our work will promote further research towards a more robust real-world detection system.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

You Only Cut Once: Boosting Data Augmentation with a Single Cut

We present You Only Cut Once (YOCO) for performing data augmentations. YOCO cuts one image into two pieces and performs data augmentations individually within each piece. Applying YOCO improves the diversity of the augmentation per sample and encourages neural networks to recognize objects from partial information. YOCO enjoys the properties of parameter-free, easy usage, and boosting almost all augmentations for free. Thorough experiments are conducted to evaluate its effectiveness. We first demonstrate that YOCO can be seamlessly applied to varying data augmentations, neural network architectures, and brings performance gains on CIFAR and ImageNet classification tasks, sometimes surpassing conventional image-level augmentation by large margins. Moreover, we show YOCO benefits contrastive pre-training toward a more powerful representation that can be better transferred to multiple downstream tasks. Finally, we study a number of variants of YOCO and empirically analyze the performance for respective settings. Code is available at GitHub.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Cross-Correlated Attention Networks for Person Re-Identification

Deep neural networks need to make robust inference in the presence of occlusion, background clutter, pose and viewpoint variations -- to name a few -- when the task of person re-identification is considered. Attention mechanisms have recently proven to be successful in handling the aforementioned challenges to some degree. However previous designs fail to capture inherent inter-dependencies between the attended features; leading to restricted interactions between the attention blocks. In this paper, we propose a new attention module called Cross-Correlated Attention (CCA); which aims to overcome such limitations by maximizing the information gain between different attended regions. Moreover, we also propose a novel deep network that makes use of different attention mechanisms to learn robust and discriminative representations of person images. The resulting model is called the Cross-Correlated Attention Network (CCAN). Extensive experiments demonstrate that the CCAN comfortably outperforms current state-of-the-art algorithms by a tangible margin.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Variations in Human Motion via Mix-and-Match Perturbation

Human motion prediction is a stochastic process: Given an observed sequence of poses, multiple future motions are plausible. Existing approaches to modeling this stochasticity typically combine a random noise vector with information about the previous poses. This combination, however, is done in a deterministic manner, which gives the network the flexibility to learn to ignore the random noise. In this paper, we introduce an approach to stochastically combine the root of variations with previous pose information, which forces the model to take the noise into account. We exploit this idea for motion prediction by incorporating it into a recurrent encoder-decoder network with a conditional variational autoencoder block that learns to exploit the perturbations. Our experiments demonstrate that our model yields high-quality pose sequences that are much more diverse than those from state-of-the-art stochastic motion prediction techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Mosaic Super-resolution via Sequential Feature Pyramid Networks

Advances in the design of multi-spectral cameras have led to great interests in a wide range of applications, from astronomy to autonomous driving. However, such cameras inherently suffer from a trade-off between the spatial and spectral resolution. In this paper, we propose to address this limitation by introducing a novel method to carry out super-resolution on raw mosaic images, multi-spectral or RGB Bayer, captured by modern real-time single-shot mosaic sensors. To this end, we design a deep super-resolution architecture that benefits from a sequential feature pyramid along the depth of the network. This, in fact, is achieved by utilizing a convolutional LSTM (ConvLSTM) to learn the inter-dependencies between features at different receptive fields. Additionally, by investigating the effect of different attention mechanisms in our framework, we show that a ConvLSTM inspired module is able to provide superior attention in our context. Our extensive experiments and analyses evidence that our approach yields significant super-resolution quality, outperforming current state-of-the-art mosaic super-resolution methods on both Bayer and multi-spectral images. Additionally, to the best of our knowledge, our method is the first specialized method to super-resolve mosaic images, whether it be multi-spectral or Bayer.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Transferring Cross-domain Knowledge for Video Sign Language Recognition

Word-level sign language recognition (WSLR) is a fundamental task in sign language interpretation. It requires models to recognize isolated sign words from videos. However, annotating WSLR data needs expert knowledge, thus limiting WSLR dataset acquisition. On the contrary, there are abundant subtitled sign news videos on the internet. Since these videos have no word-level annotation and exhibit a large domain gap from isolated signs, they cannot be directly used for training WSLR models. We observe that despite the existence of a large domain gap, isolated and news signs share the same visual concepts, such as hand gestures and body movements. Motivated by this observation, we propose a novel method that learns domain-invariant visual concepts and fertilizes WSLR models by transferring knowledge of subtitled news sign to them. To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features. In order to learn domain-invariant features within each class and suppress domain-specific features, our method further resorts to an external memory to store the class centroids of the aligned news signs. We then design a temporal attention based on the learnt descriptor to improve recognition performance. Experimental results on standard WSLR datasets show that our method outperforms previous state-of-the-art methods significantly. We also demonstrate the effectiveness of our method on automatically localizing signs from sign news, achieving 28.1 for AP@0.5.

0 citations0 reviewsNo code linkedOpen access