Searcharxiv⌕ Search

arXiv subjects

Amarnath R

Publications and source records attributed to Amarnath R.

9 recordsLinked to original sources

Action Transfer Across Character Body Plans in Latent-Action World Models: An Empirical Study of Animated Characters

Latent-action world models learn actions from video without labels, and recent methods aim to share these actions across bodies. Transfer between 2D characters with different body structures remains underexplored. In this paper, we study whether an action learned from one character can make a character with a different body perform the same action. A cat, a blob and a human can all jump, but each moves its body in its own way. The usual transfer gain mixes body motion with screen movement and can assign a perfect score to a model that ignores its action. To address this, we introduce a transfer score that compares the correct action with wrong ones from the same source. We test five training objectives on a new synthetic benchmark of 2D cartoon characters with six body plans, the standard Sprites benchmark, and 431 selected animal and human animations from DeformingThings4D. With a fixed camera, a baseline that only copies the source's screen movement scores 0.71, as high as most learned models. In contrast, with a camera that follows the body, the best model reaches only 0.46 for an unseen animal family and 0.20 for humans. With this camera, a linear probe identifies the action class of unseen animal families with 66% to 86% balanced accuracy (chance 17%). The learned actions therefore retain information about which action is performed, but the correct action closes only part of the prediction error gap for a new character.

cs.CV↗

Learning the Past from the Future: Retrospective Reconstruction in Temporal Interaction Networks

Temporal link prediction uses past interactions to predict future links. In practice, interaction records from web and mobile applications can contain gaps caused by logging failures, API limits or lost records, even when later events remain available. To our knowledge, the extent to which later events help recover interactions within such gaps has not been measured directly for this ranking task. We study retrospective reconstruction using the tgbl-wiki and tgbl-comment datasets. We hide a two-hour window, use its interactions as ground truth, and rank the directed pairs active within it. We compare count-based heuristics and logistic regression models using past information alone or together with 1, 6 or 24 hours of later events. Target pairs and candidate lists remain fixed across conditions, so differences in ranking performance cannot be attributed to changes in candidate selection. With 24 hours of later events, the 26-feature logistic regression improves mean reciprocal rank (MRR) by 0.039 on tgbl-wiki under exhaustive ranking, 0.046 under historical-random ranking, and 0.108 on tgbl-comment under historical-random ranking. The 26-feature logistic regression benefits from adding later features to past features, whereas replacing the past pair count with the later pair count reduces MRR by 0.157 on tgbl-wiki under exhaustive ranking. A control removing later interactions from query sources to historically observed destinations reduces the MRR gain by 59% on tgbl-wiki and 10% on tgbl-comment. Because this control removes more than repeated target pairs, these reductions cannot be attributed to pair recurrence alone. Later events improve the ranking of hidden interactions on both datasets, including tgbl-comment, where only 6.4% of target pairs reappeared within 24 hours.

cs.SI↗

Effect of Input Resolution on Retinal Vessel Segmentation Performance: An Empirical Study Across Five Datasets

Most deep learning pipelines for retinal vessel segmentation resize fundus images to satisfy GPU memory constraints and enable uniform batch processing. However, the impact of this resizing on thin vessel detection remains underexplored. When high resolution images are downsampled, thin vessels are reduced to subpixel structures, causing irreversible information loss even before the data enters the network. Standard volumetric metrics such as the Dice score do not capture this loss because thick vessel pixels dominate the evaluation. We investigated this effect by training a baseline UNet at multiple downsampling ratios across five fundus datasets (DRIVE, STARE, CHASE_DB1, HRF, and FIVES) with native widths ranging from 565 to 3504 pixels, keeping all other settings fixed. We introduce a width-stratified sensitivity metric that evaluates thin (half-width <3 pixels), medium (3 to 7 pixels), and thick (>7 pixels) vessel detection separately, using native resolution width estimates derived from a Euclidean distance transform. Results show that for high-resolution datasets (HRF, FIVES), thin vessel sensitivity improves monotonically as images are downsampled toward the encoder's effective operating range, peaking at processed widths between 256 and 876 pixels. For low-to-mid resolution datasets (DRIVE, STARE, CHASE_DB1), thin vessel sensitivity is highest at or near native resolution and degrades with any downsampling. Across all five datasets, aggressive downsampling reduced thin vessel sensitivity by up to 15.8 percentage points (DRIVE) while Dice remained relatively stable, confirming that Dice alone is insufficient for evaluating microvascular segmentation.

cs.CV↗

HMS-VesselNet: Hierarchical Multi-Scale Attention Network with Topology-Preserving Loss for Retinal Vessel Segmentation

Retinal vessel segmentation methods based on standard overlap losses tend to miss thin peripheral vessels because these structures occupy very few pixels and have low contrast against the background. We propose HMS-VesselNet, a hierarchical multi-scale network that processes fundus images across four parallel branches at different resolutions and combines their outputs using learned fusion weights. The training loss combines Dice, binary cross-entropy, and centerline Dice to jointly optimize area overlap and vessel continuity. Hard example mining is applied from epoch 20 onward to concentrate gradient updates on the most difficult training images. Tested on 68 images from DRIVE, STARE, and CHASE_DB1 using 5-fold cross-validation, the model achieves a mean Dice of 88.72 +/- 0.67%, Sensitivity of 90.78 +/- 1.42%, and AUC of 98.25 +/- 0.21%. In leave-one-dataset-out experiments, AUC remains above 95% on each unseen dataset. The largest improvement is in the recall of thin peripheral vessels, which are the structures most frequently missed by standard methods and most critical for early detection of diabetic retinopathy.

eess.IV↗

Pruning Distorted Images in MNIST Handwritten Digits

Recognizing handwritten digits is a challenging task primarily due to the diversity of writing styles and the presence of noisy images. The widely used MNIST dataset, which is commonly employed as a benchmark for this task, includes distorted digits with irregular shapes, incomplete strokes, and varying skew in both the training and testing datasets. Consequently, these factors contribute to reduced accuracy in digit recognition. To overcome this challenge, we propose a two-stage deep learning approach. In the first stage, we create a simple neural network to identify distorted digits within the training set. This model serves to detect and filter out such distorted and ambiguous images. In the second stage, we exclude these identified images from the training dataset and proceed to retrain the model using the filtered dataset. This process aims to improve the classification accuracy and confidence levels while mitigating issues of underfitting and overfitting. Our experimental results demonstrate the effectiveness of the proposed approach, achieving an accuracy rate of over 99.5% on the testing dataset. This significant improvement showcases the potential of our method in enhancing digit classification accuracy. In our future work, we intend to explore the scalability of this approach and investigate techniques to further enhance accuracy by reducing the size of the training data.

cs.CV↗

Word and character segmentation directly in run-length compressed handwritten document images

From the literature, it is demonstrated that performing text-line segmentation directly in the run-length compressed handwritten document images significantly reduces the computational time and memory space. In this paper, we investigate the issues of word and character segmentation directly on the run-length compressed document images. Primarily, the spreads of the characters are intelligently extracted from the foreground runs of the compressed data and subsequently connected components are established. The spacing between the connected components would be larger between the adjacent words when compared to that of intra-words. With this knowledge, a threshold is empirically chosen for inter-word separation. Every connected component within a word is further analysed for character segmentation. Here, min-cut graph concept is used for separating the touching characters. Over-segmentation and under-segmentation issues are addressed by insertion and deletion operations respectively. The approach has been developed particularly for compressed handwritten English document images. However, the model has been tested on non-English document images.

cs.CV↗

Text line Segmentation in Compressed Representation of Handwritten Document using Tunneling Algorithm

In this research work, we perform text line segmentation directly in compressed representation of an unconstrained handwritten document image. In this relation, we make use of text line terminal points which is the current state-of-the-art. The terminal points spotted along both margins (left and right) of a document image for every text line are considered as source and target respectively. The tunneling algorithm uses a single agent (or robot) to identify the coordinate positions in the compressed representation to perform text-line segmentation of the document. The agent starts at a source point and progressively tunnels a path routing in between two adjacent text lines and reaches the probable target. The agent's navigation path from source to the target bypassing obstacles, if any, results in segregating the two adjacent text lines. However, the target point would be known only when the agent reaches the destination; this is applicable for all source points and henceforth we could analyze the correspondence between source and target nodes. Artificial Intelligence in Expert systems, dynamic programming and greedy strategies are employed for every search space while tunneling. An exhaustive experimentation is carried out on various benchmark datasets including ICDAR13 and the performances are reported.

cs.CV↗

Novel approach to locate region of interest in mammograms for Breast cancer

Locating region of interest for breast cancer masses in the mammographic image is a challenging problem in medical image processing. In this research work, the keen idea is to efficiently extract suspected mass region for further examination. In particular to this fact breast boundary segmentation on sliced rgb image using modified intensity based approach followed by quad tree based division to spot out suspicious area are proposed in the paper. To evaluate the performance DDSM standard dataset are experimented and achieved acceptable accuracy.

cs.CV↗

Spotting Separator Points at Line Terminals in Compressed Document Images for Text-line Segmentation

Line separators are used to segregate text-lines from one another in document image analysis. Finding the separator points at every line terminal in a document image would enable text-line segmentation. In particular, identifying the separators in handwritten text could be a thrilling exercise. Obviously it would be challenging to perform this in the compressed version of a document image and that is the proposed objective in this research. Such an effort would prevent the computational burden of decompressing a document for text-line segmentation. Since document images are generally compressed using run length encoding (RLE) technique as per the CCITT standards, the first column in the RLE will be a white column. The value (depth) in the white column is very low when a particular line is a text line and the depth could be larger at the point of text line separation. A longer consecutive sequence of such larger depth should indicate the gap between the text lines, which provides the separator region. In case of over separation and under separation issues, corrective actions such as deletion and insertion are suggested respectively. An extensive experimentation is conducted on the compressed images of the benchmark datasets of ICDAR13 and Alireza et al [17] to demonstrate the efficacy.

cs.CV↗