 |
 |
 |
 |
 |
 |
||
 |
 |
 |
 |
 |
| 5 | 1/1 | 返回列表 |
| 查看: 3506 | 回復(fù): 18 | |||
| 當(dāng)前只顯示滿足指定條件的回帖，點擊這里查看本話題的所有回帖 | |||
smallbug2000木蟲 (著名寫手)
|
[求助]
哥的論文大修，哥很郁悶，哥不想改了
|
||
|
投了一篇論文到計算機視覺相關(guān)的雜志，最近返回結(jié)果，三個審稿人，其中兩個審稿人意見較少。另一個覺得算法的創(chuàng)新性不夠，給了大修，悲劇的是這篇論文之前投到CVPR去，也是這個審稿人審的（CVPR據(jù)了我），因為審稿意見基本一樣，故可以斷定是同一審稿人。最終編輯給了大修，但是我很絕望，因為給大修的審稿人從一開始就不認(rèn)可我的算法，我想既然我認(rèn)真修改了，可能還是會被他據(jù)。將編輯及大修審稿人意見附后，在此向各位大牛咨詢兩件事：1）該論文是否值得大修，修后被據(jù)的概率多大？2）如果大修，如果對付審稿人這么尖銳的問題。在些感謝，對于好的建議發(fā)放金幣。 Dear**, Reviewers have now commented on your paper. You will see that they are advising that you revise your manuscript. If you are prepared to undertake the work required, I would be pleased to reconsider my decision. The reviewers' comments can be found at the end of this email or can be accessed by following the provided link. Reviewers' comments: The paper was reviewed by three experts on the topic. The reviewers agree that the paper discusses an important problem worth pursuing. They, however, also unanimously point out short comings of the paper, most important of which is the lack of thorough theoretical and experimental validation of the claims as well as references to prior work. The paper needs major revision to be considered for publication. If the authors decide to submit a major revision, please make sure to address the points raised by the reviewers. Reviewer #2: : This paper deals with the problem of visual tracking with irregular object motion. The particle set shift approach based on analytic optimization is proposed to deal with the incorrect state dynamic model. Particles are first sampled by the state dynamic model and they are moved to higher likelihood regions by newton optimization by maximizing likelihoods. The efficacy of the proposed approach is demonstrated via experiments with real sequences. - Positive points: Practically effective approach - Negative points: Not novel approach, rather heuristic, not convincing experimental results : The main problem of this paper is the proposed approach is not novel. The proposed approach is quite similar to [18] except the fact that the proposed approach used newton optimization instead of mean shift. : The proposed approach is rather heuristic. In the algorithm, particle weights are only proportional to likelihood, and this holds true for SIR particle filter where particles are sampled from state dynamic model. However, since particles are moved to higher likelihoods artificially, the weights determined from likelihoods will no longer correctly represent the true posterior. The proposed approach is rather similar to the particle swarm optimization-based tracking, e.g., "" by X. ** et al in CVPR 2008. Another problem of the proposed approach is that it might result in worse tracking results when there are appearance changes caused by various issues such as pose and lighting changes. : Since the proposed work is based on particle filter, the optimal importance functions used for visual tracking are also relevant. If we can use the optimal importance function, the irregular motion can be handled at least partially. Thus the following papers should be cited and commented as related work: - : The supplementary video result is too limited. Only a result for a single short sequence is not sufficient to support the validity of the proposed approach. Why is there no rotational motion in the results? The paper says that the state is translation, scale, and rotation, but there is no rotational motion in the results in the paper and video. : There must be cases that all particles are outside the basin of convergence. Since the particle are shifted by local optimization, particles will diverge from the optimal positions and tracking will fail. In the proposed approach, there is no consideration of this possibility. : The optimization will increase the computational complexity considerably. It is necessary to compare the other algorithms under the same computational time, e.g., proposed framework with 100 particles and standard particle filter with 1000 particles. My current recommendation is major revision. If the authors want to make the paper accepted in spite of the limited novelty and contribution, I think the followings should be addressed in the revision: - Additional experiments with object appearance changes like illumination - Addition of a mechanism to deal with the local optima problems with additional experiments with related videos - Comparison under the same computational complexity for different tracking algorithms [ Last edited by smallbug2000 on 2012-9-6 at 09:52 ] |
回復(fù)此樓» 收錄本帖的淘帖專輯推薦
 文章寫作 |
» 猜你喜歡
362求調(diào)劑
已經(jīng)有14人回復(fù)
-
求調(diào)劑 302分初試 0854
已經(jīng)有4人回復(fù)
-
299求調(diào)劑
已經(jīng)有4人回復(fù)
-
266分，一志愿電氣工程，本科材料，求材料專業(yè)調(diào)劑
已經(jīng)有3人回復(fù)
-
312求調(diào)劑
已經(jīng)有4人回復(fù)
-
315求調(diào)劑
已經(jīng)有7人回復(fù)
-
土木304求調(diào)劑
已經(jīng)有3人回復(fù)
-
316求調(diào)劑
已經(jīng)有16人回復(fù)
-
一志愿華東理工大學(xué)，080500學(xué)碩，317分，求調(diào)劑
已經(jīng)有13人回復(fù)
-
材料與化工306分找調(diào)劑
已經(jīng)有9人回復(fù)
» 本主題相關(guān)價值貼推薦，對您同樣有幫助:
- 哥一直修改論文到現(xiàn)在
已經(jīng)有29人回復(fù)
- 修改意見是小修還是大修？已經(jīng)又返回去外審了，不懂！求教！
已經(jīng)有9人回復(fù)
- 還是reject and resubmitted
已經(jīng)有8人回復(fù)
- SCI論文大修意見中有一條修改意見不知道理解的對不對，請高手幫看看
已經(jīng)有11人回復(fù)
- 文章從major revision到 reject and resubmitted怎么回事？
已經(jīng)有16人回復(fù)
- 不想按評審意見全部重寫一遍，后果怎樣
已經(jīng)有10人回復(fù)
- JMCA投稿后大修，返回修改稿后收到郵件，不懂什么意思啊，求大神幫忙
已經(jīng)有8人回復(fù)
- BMCL文章大修，不是很理解審稿意見，求指導(dǎo)從哪個角度進(jìn)行文章修改
已經(jīng)有6人回復(fù)
- 這個算是大改還是小改？
已經(jīng)有7人回復(fù)
- 論文第二次讓大修！
已經(jīng)有20人回復(fù)
- 同一篇論文連續(xù)第三次給大修有沒有�。�
已經(jīng)有24人回復(fù)
- 論文一審回來后，大修，但是想更換些好的實驗數(shù)據(jù)，可否？
已經(jīng)有5人回復(fù)
- SCI文章大修,四個審稿人,有一個不同意發(fā)表,大修返回后,據(jù)的這個審稿人態(tài)度會改變嗎
已經(jīng)有15人回復(fù)
- 請教：論文大修，機會大不大？三個月修改期限，多長時間提交修改稿較好？謝謝！
已經(jīng)有11人回復(fù)
- 稿件被編輯婉拒后，還可以再投給該期刊的其他編輯嗎？
已經(jīng)有19人回復(fù)
- 論文大修 郁悶
已經(jīng)有19人回復(fù)
- 被一個雜志據(jù)稿，但是編輯說按照要求修改可以重投稿，如何回編輯的信件？
已經(jīng)有8人回復(fù)
- 文章大修，修改期限降至，能不能向主編申請延期上交修改稿件？
已經(jīng)有6人回復(fù)
- 論文被拒，編輯意見改后重投
已經(jīng)有15人回復(fù)
- 請問這種情況是大修還是小修，另外reviewer的建議需不需要改？
已經(jīng)有7人回復(fù)
- 文章大修，修改列表需要重復(fù)point-to-point 的修改細(xì)節(jié)嗎？
已經(jīng)有8人回復(fù)
- 論文大修，問題一大堆，修改意見四頁多，修后錄用可能性大不？
已經(jīng)有30人回復(fù)
寒山聽雪
鐵蟲 (小有名氣)
- 應(yīng)助: 4 (幼兒園)
- 金幣: 67.2
- 散金: 14
- 帖子: 80
- 在線: 24.3小時
- 蟲號: 1894930
- 注冊: 2012-07-16
- 性別: GG
- 專業(yè): 生物信息學(xué)
5樓2012-09-06 15:42:20
carsonwen
銅蟲 (小有名氣)
- 應(yīng)助: 1 (幼兒園)
- 金幣: 177.4
- 散金: 10
- 帖子: 71
- 在線: 11.6小時
- 蟲號: 44277
- 注冊: 2004-04-24
- 性別: GG
- 專業(yè): 信息處理方法與技術(shù)
2樓2012-09-06 10:30:45
flywithyu
銅蟲 (小有名氣)
- 應(yīng)助: 6 (幼兒園)
- 金幣: 103.8
- 帖子: 82
- 在線: 17.6小時
- 蟲號: 1630735
- 注冊: 2012-02-21
- 專業(yè): 信息處理方法與技術(shù)
【答案】應(yīng)助回帖
★ ★ ★ ★ ★ ★ ★ ★ ★ ★
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 14:45:35
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:37:34
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-11 19:27:09
smallbug2000: 金幣+4, ★★★★★最佳答案 2012-09-13 14:47:15
感謝參與，應(yīng)助指數(shù) +1
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 14:45:35
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-06 17:37:34
smallbug2000: 金幣+2, ★★★很有幫助 2012-09-11 19:27:09
smallbug2000: 金幣+4, ★★★★★最佳答案 2012-09-13 14:47:15
|
這個修改意見不算多的，具體就是： 1、增加實驗結(jié)果以驗證你方法的有效性；（這個只要有數(shù)據(jù)，應(yīng)該好辦） 2、局部最優(yōu)問題，這個較難回答，一種你找到方法；另外一種就是通過實驗來說明； 3、與不同算法的比較。首先找找網(wǎng)上有沒有現(xiàn)成的能出結(jié)果的代碼吧；實在不行只有自己實現(xiàn)；話說實驗室如果有做換個方向的話應(yīng)該是有一定基礎(chǔ)吧。 強烈建議：按照專家意見修改，不要回避，最終你會發(fā)現(xiàn)有收獲的！！  |
3樓2012-09-06 12:27:52
wangzhipengj
至尊木蟲 (文壇精英)
- 應(yīng)助: 240 (大學(xué)生)
- 金幣: 21356.1
- 散金: 5
- 紅花: 43
- 帖子: 10888
- 在線: 551.1小時
- 蟲號: 1702123
- 注冊: 2012-03-19
- 專業(yè): 高分子合成化學(xué)
4樓2012-09-06 13:05:39
| 最具人氣熱帖推薦 [查看全部] | 作者 | 回/看 | 最后發(fā)表 | |
|---|---|---|---|---|
|
[考研] 319求調(diào)劑 +14 | 太容易1018 2026-04-01 | 14/700 |
|
|---|---|---|---|---|
|
|
[考研] 280求調(diào)劑 +8 | 咕嚕曉曉 2026-04-02 | 9/450 |
|
|
|
[考研] 310求調(diào)劑 +17 | 爭取九點睡 2026-03-30 | 17/850 |
|
|
[考研] 總分328生物與醫(yī)藥考數(shù)學(xué)求調(diào)劑 +3 | aaadim 2026-04-02 | 3/150 |
|
|
|
[考研] 266求調(diào)劑 +4 | 學(xué)員97LZgn 2026-04-02 | 4/200 |
|
|
|
[考研] 0817化工學(xué)碩調(diào)劑 +11 | 努力上岸中！ 2026-03-31 | 11/550 |
|
|
|
[考研] 070300一志愿211，312分求調(diào)劑院校 +14 | 小黃鴨寶 2026-03-30 | 14/700 |
|
|
|
[考研] 265求調(diào)劑 +11 | yelck 2026-04-01 | 12/600 |
|
|
|
[考研] 353求調(diào)劑 +4 | 拉鉤不許變 2026-04-01 | 4/200 |
|
|
|
[考研] 349求調(diào)劑 +6 | 吃的不少 2026-04-01 | 6/300 |
|
|
|
[考研] 0856，材料與化工321分求調(diào)劑 +13 | 大饞小子 2026-03-27 | 14/700 |
|
|
|
[考研] 省雙一流重點一本大學(xué)招收調(diào)劑 +4 | wwwwffffff 2026-03-31 | 7/350 |
|
|
|
[考研] 08工科275求調(diào)劑，可跨考。 +5 | AaAa7420 2026-03-31 | 5/250 |
|
|
|
[考研] 求調(diào)劑 生物學(xué) 377分 +6 | zzll03 2026-03-31 | 6/300 |
|
|
|
[考研] 353求調(diào)劑 +3 | 江上楓_26 2026-03-28 | 3/150 |
|
|
|
[考研] 南京大學(xué)化學(xué)調(diào)劑 +11 | 景隨風(fēng) 2026-03-29 | 16/800 |
|
|
|
[考研] 08工科求調(diào)劑286 +5 | tgs_001 2026-03-28 | 5/250 |
|
|
|
[考研] 調(diào)劑考研 +3 | 王杰一 2026-03-29 | 3/150 |
|
|
|
[考研] 265求調(diào)劑 +8 | 小木蟲085600 2026-03-27 | 8/400 |
|
|
|
[考研] 一志愿上海理工能源動力（085800）310分求調(diào)劑 +3 | zhangmingc 2026-03-27 | 4/200 |
|